Method and device for generating target point cloud data, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a method and device for generating target point cloud data, electronic equipment and a storage medium, and the method comprises the steps: carrying out the projection processing of a plurality of pieces of to-be-processed point cloud data, obtaining a plurality of pieces of to-be-used point cloud data, and enabling the values of the to-be-used point cloud data to be the same in a first direction; randomly generating a to-be-processed area based on the to-be-used point cloud data, and determining to-be-applied point cloud data in the to-be-processed area; after a pre-created three-dimensional grid model corresponding to the to-be-processed area is fused to the to-be-processed area, target point cloud data corresponding to the to-be-applied point cloud data is determined based on the to-be-applied point cloud data and the three-dimensional grid model; wherein the target point cloud data is the point cloud data corresponding to the preset object category. According to the technical scheme provided by the embodiment of the invention, the effects of high efficiency and convenience of generating the target point cloud data of the preset object type can be improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data processing technology, and in particular, to a method, device, electronic device and storage medium for generating target point cloud data. Background Art

[0002] With the development of intelligence, autonomous driving has become a development trend. In the autonomous driving scenario, identifying specific objects plays a vital role in path planning and obstacle avoidance. Usually, laser radar is used in autonomous driving, and the point cloud data collected by it can accurately depict the information of environmental objects within the collection range, thereby achieving the effect of identifying specific objects.

[0003] For some potholes below the ground, accurate identification is a great challenge for autonomous driving algorithms. Currently, the identification of potholes mainly requires collecting enough point cloud data corresponding to the potholes, and then determining whether the collected point cloud data corresponds to the potholes based on such point cloud data.

[0004] However, for point cloud data of potholes, the autonomous driving data collection vehicle needs to be driven near the potholes to collect data, which is inconvenient. Furthermore, since potholes are not common, when generating potholes based on external forces, there are problems of high labor costs and limited amount of point cloud data corresponding to potholes. Summary of the invention

[0005] Embodiments of the present invention provide a method, an apparatus, an electronic device, and a storage medium for generating target point cloud data, so as to achieve the effect of efficiently generating target point cloud data of a preset object type.

[0006] In a first aspect, an embodiment of the present invention provides a method for generating target point cloud data, the method comprising:

[0007] By projecting a plurality of point cloud data to be processed, a plurality of point cloud data to be used is obtained, wherein the values ​​of the point cloud data to be used in the first direction are the same;

[0008] Randomly generate a to-be-processed area based on the to-be-used point cloud data, and determine the to-be-applied point cloud data located in the to-be-processed area;

[0009] After fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed, determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model;

[0010] The target point cloud data is point cloud data corresponding to a preset object category.

[0011] Furthermore, the randomly generating a to-be-processed area based on the to-be-used point cloud data, and determining the to-be-applied point cloud data located in the to-be-processed area, comprises:

[0012] Randomly generate a to-be-screened area based on the to-be-used point cloud data;

[0013] When the object category of the point cloud data to be used in the area to be screened does not include at least one preset point cloud category, the area to be screened is used as the area to be processed;

[0014] The point cloud data to be used located in the area to be processed is determined according to the area coordinate information of the area to be processed and the point cloud coordinate information of the point cloud data to be used.

[0015] Furthermore, the method further comprises:

[0016] Based on the area coordinate information of the area to be processed, the three-dimensional mesh model is created; wherein the three-dimensional mesh model is composed of a plurality of triangular meshes, and the attribute information of each mesh point includes the coordinates of the mesh to be processed;

[0017] Processing the grid coordinates to be processed in the three-dimensional grid model based on the coordinate transformation matrix between the three-dimensional grid coordinate system and the target coordinate system to obtain a three-dimensional grid model with updated attribute information;

[0018] The target coordinate system is a coordinate system corresponding to when collecting the point cloud data to be processed.

[0019] Furthermore, after the three-dimensional grid model is fused to the area to be processed, the depth of the area to be processed is the height of the three-dimensional grid model. Accordingly, the area to be processed is a three-dimensional space area.

[0020] Furthermore, the determining, based on the point cloud data to be applied and the three-dimensional grid model, target point cloud data corresponding to the point cloud data to be applied includes:

[0021] For the point cloud data to be applied, based on the point cloud data to be applied and the coordinate origin of the target coordinate system, determining a target ray corresponding to the point cloud data to be applied;

[0022] Based on the target ray and the grid point coordinates of the three-dimensional grid model located in the area to be processed, the target point cloud data corresponding to the point cloud data to be applied is determined.

[0023] Furthermore, after obtaining the target point cloud data, the method further includes:

[0024] Determining the reflectivity corresponding to the area to be processed according to the material information corresponding to the area to be processed;

[0025] The target point cloud data is updated based on the reflectivity.

[0026] Furthermore, the object category corresponding to the target point cloud data is the same as the preset object category corresponding to the pothole area.

[0027] In a second aspect, an embodiment of the present invention further provides a data processing device, the device comprising:

[0028] a module for determining point cloud data to be used, configured to obtain a plurality of point cloud data to be used by projecting a plurality of point cloud data to be processed, wherein the values ​​of the point cloud data to be used in the first direction are the same;

[0029] A module for determining point cloud data to be applied, used for randomly generating a region to be processed based on the point cloud data to be used, and determining the point cloud data to be applied located in the region to be processed;

[0030] a target point cloud data determination module, configured to determine target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model after fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed;

[0031] The target point cloud data is point cloud data corresponding to a preset object category.

[0032] In a third aspect, an embodiment of the present invention provides a server, which includes:

[0033] one or more processors;

[0034] A memory for storing one or more programs;

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating target point cloud data provided by any embodiment of the present invention.

[0036] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for generating target point cloud data as provided in any embodiment of the present invention.

[0037] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the method for generating target point cloud data as described in any one of the embodiments of the present invention.

[0038] The technical solution provided by the embodiment of the present invention can project the point cloud data to be processed after obtaining the point processing point cloud data to obtain the point cloud data to be used with the same numerical value in the first direction. Next, the area to be processed is randomly generated based on the point cloud data to be used, and the point cloud data to be applied located in the area to be processed is determined. The pothole area can be simulated, a three-dimensional grid model corresponding to the area to be processed can be created, and the three-dimensional grid model can be fused to the area to be processed. Here, according to the point cloud data to be applied and the area to be processed fused with the three-dimensional grid model, the target point cloud data corresponding to the pothole area corresponding to the area to be processed projected by each point cloud data to be applied can be determined. It is realized that the simulation-based method can efficiently and conveniently generate the target point cloud data corresponding to the preset object type, which solves the problem of high cost and low efficiency in generating the target point cloud data corresponding to the preset object type in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flowchart of a method for generating target point cloud data provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram obtained after projecting the point cloud data to be processed provided by an embodiment of the present invention;

[0042] Figure 3 A flowchart of a method for generating target point cloud data provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of a generated 3D mesh provided by an embodiment of the present invention;

[0044] Figure 5 A schematic diagram of annotating target point cloud data provided by an embodiment of the present invention;

[0045] Figure 6 A schematic diagram of the structure of a data processing device provided by an embodiment of the present invention;

[0046] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0049] Before introducing the technical solution provided by the embodiment of the present invention, an application scenario may be exemplified first.

[0050] In the vicinity of the construction area scene, there are usually deep construction pits that are lower than the ground. Accurately identifying the deep pits is a great challenge for the autonomous driving algorithm. The deep pit area can be simulated based on the solution provided in the embodiment of the present invention, and then the target point cloud data corresponding to the deep pit area can be generated.

[0051] It should be noted that each point cloud file includes tens of thousands of point cloud data, and each point cloud data includes three-dimensional space coordinates and reflectivity. The number of images corresponding to the point cloud file can be one or more. In order to generate point cloud data corresponding to the preset object category, the point cloud data corresponding to each image can be processed. At the same time, the processing method for the point cloud data of each image is the same. Here, the point cloud data processing of one of the images is used as an example to illustrate. The point cloud data corresponding to the image currently introduced is called the point cloud data to be processed.

[0052] Figure 1 A flowchart of a method for generating target point cloud data provided in an embodiment of the present invention. This embodiment can be applied to a scenario in which target point cloud data corresponding to a preset object type is generated. The preset object type can be a type corresponding to a deep pit area. The method for generating target point cloud data provided in this embodiment can be executed by a device for generating target point cloud data. The device can be integrated in a server or an electronic device. The electronic device can be a mobile terminal or a PC terminal.

[0053] like Figure 1 As shown, the method specifically comprises the following steps:

[0054] S110 , obtaining a plurality of point cloud data to be used by projecting a plurality of point cloud data to be processed, wherein the values ​​of the point cloud data to be used in the first direction are the same.

[0055] Among them, the point cloud data of a certain image is constructed as the point cloud data to be processed. The point cloud data to be processed can be characterized by three-dimensional coordinates and reflectivity. The point cloud data to be processed is three-dimensional point cloud data, so the objects in the space can be reconstructed. As for the pothole area, for example, the pothole area with a certain depth value is mainly concentrated on the ground, so the point cloud data to be processed can be projected to obtain point cloud data located on the same horizontal plane, and the point cloud data obtained at this time is used as the point cloud data to be used. At this time, the first direction can be a direction perpendicular to the horizontal plane. If represented in the form of coordinates, the first direction can be the Z direction.

[0056] In this embodiment, the point cloud data to be processed is projected to obtain the point cloud data to be used with the same numerical value in the first direction. The advantage is that the point cloud data to be processed can be projected to the same horizontal plane to obtain the point cloud data to be used that can simulate the ground.

[0057] The method of projecting the point cloud data to be processed may be: after projecting the point cloud data to be processed to a BEV (BirdEye View) perspective, the point cloud data to be used may be obtained.

[0058] S120 , randomly generating a to-be-processed area based on the to-be-used point cloud data, and determining the to-be-applied point cloud data located in the to-be-processed area.

[0059] The area to be processed is a randomly generated area. The shape of the area to be processed can be a pre-set shape or a randomly generated shape. In order to improve the richness of the target point cloud data and thus the accuracy of the recognition of the preset object type point cloud data in autonomous driving, the shape of the area to be processed can be any shape. The point cloud data to be used within the area to be processed is used as the point cloud data to be applied, that is, the point cloud data to be applied is the point cloud data inside the area to be processed.

[0060] Specifically, after obtaining the point cloud data to be used, a region to be processed can be randomly generated. After obtaining the region to be processed, in order to simulate the target point cloud data located in the pothole area (a deep pit area with a fixed depth value), the point cloud data to be applied located in the same plane and in the region to be processed can be obtained first.

[0061] For example, see Figure 2 After the point cloud data to be processed is projected and the point cloud data to be used is obtained, a region to be processed may be randomly selected, and the region to be processed may be a rectangular region. Figure 2 The yellow rectangle in the middle is the position of the autonomous driving vehicle, and the white rectangle is the randomly selected area to be processed. The point cloud data in the area to be processed can be obtained as the point cloud data to be applied.

[0062] It should be noted that there are only ground points located on the same horizontal plane in the area to be processed, and there are no points of other object categories such as pedestrians and vehicles.

[0063] S130, after fusing the pre-created three-dimensional grid model corresponding to the area to be processed into the area to be processed, determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model.

[0064] The target point cloud data is point cloud data corresponding to a preset object category. The preset object category is a category pre-set as a pothole area.

[0065] In order to process the two-dimensional area to be processed into a pothole area with a depth value, that is, a deep pit area, a three-dimensional grid model can be created. The bottom size of the three-dimensional grid model is the same as the size of the area to be processed. The height of the three-dimensional grid model can be set according to the height information of the required deep pit area. After the three-dimensional grid model is fused with the area to be processed, the area to be processed with simulated deep pit information is obtained. After fusion, the target point cloud data can be determined based on the point cloud data to be applied and the three-dimensional grid model.

[0066] It should be noted that after the three-dimensional grid area is merged into the area to be processed, the depth of the area to be processed is the height of the three-dimensional model. Correspondingly, at this time, the area to be processed is a three-dimensional space area with a certain depth. In other words, based on this method, a deep pit area can be simulated, and then based on the relevant information of the three-dimensional grid model in the deep pit area, the target point cloud data corresponding to the deep pit area can be determined.

[0067] It can be understood that the created three-dimensional grid model can be fused with the area to be processed to obtain the area to be processed that simulates the deep pit information. Next, based on the area to be processed that is fused with the three-dimensional grid model and the point cloud data to be applied, the target point cloud data corresponding to the point cloud data to be applied in the depth area can be determined.

[0068] The technical solution provided by the embodiment of the present invention can project the point cloud data to be processed after obtaining the point processing point cloud data to obtain the point cloud data to be used with the same numerical value in the first direction. Next, the area to be processed is randomly generated based on the point cloud data to be used, and the point cloud data to be applied located in the area to be processed is determined. The pothole area can be simulated, a three-dimensional grid model corresponding to the area to be processed can be created, and the three-dimensional grid model can be fused to the area to be processed. Here, according to the point cloud data to be applied and the area to be processed fused with the three-dimensional grid model, the target point cloud data corresponding to the pothole area corresponding to the area to be processed projected by each point cloud data to be applied can be determined. It is realized that the simulation-based method can efficiently and conveniently generate the target point cloud data corresponding to the preset object type, which solves the problem of high cost and low efficiency in generating the target point cloud data corresponding to the preset object type in the prior art.

[0069] On the basis of the above technical solution, after obtaining the target point cloud data, a target neural network that can identify the deep pothole area can be trained based on the target point cloud data and the corresponding object type. The target neural network can be deployed in the autonomous driving vehicle, so that after the laser radar collects the point cloud data, the point cloud data can be analyzed and processed based on the target neural network to identify the deep pothole area on the road, thereby improving the driving safety of the autonomous driving vehicle.

[0070] Figure 3 A flow chart of a method for generating target point cloud data provided in an embodiment of the present invention, based on the above-mentioned embodiment, can further refine: "randomly generate a to-be-processed area based on the to-be-used point cloud data, and determine the to-be-applied point cloud data located in the to-be-processed area" and: "determine the target point cloud data corresponding to the to-be-applied point cloud data based on the to-be-applied point cloud data and the three-dimensional grid model". The specific implementation method can refer to the detailed description of this technical solution. Among them, the technical terms that are the same as or corresponding to the above-mentioned embodiment are not repeated in this embodiment.

[0071] like Figure 3 As shown, the method provided in this embodiment includes:

[0072] S210 , obtaining a plurality of point cloud data to be used by projecting a plurality of point cloud data to be processed, wherein the values ​​of the point cloud data to be used in the first direction are the same.

[0073] S220: randomly generate a to-be-screened area based on the to-be-used point cloud data, and when the object category of the to-be-used point cloud data within the to-be-screened area does not include at least one preset point cloud category, use the to-be-screened area as the to-be-processed area.

[0074] It should be noted that the acquired point cloud data to be processed includes not only three-dimensional coordinate data and reflectivity data, but also the object category corresponding to the point cloud data to be processed.

[0075] Among them, the area that is randomly generated based on the point cloud data to be used and has not been processed again is used as the area to be screened. The area to be screened may include multiple point cloud data, and the object category corresponding to the point cloud data can be determined. At least one preset point cloud category is an object category that cannot be included in the point cloud data in the preset area to be screened. Optionally, the preset point cloud category can be a pedestrian point cloud category, a vehicle object category, and so on. In this embodiment, when the point cloud data to be processed is displayed in the image, different display colors can be used to distinguish the object category. If the area to be screened includes the point cloud data to be applied corresponding to the preset point cloud category, the area to be screened can be used as the area to be processed.

[0076] Specifically, after randomly generating the area to be screened based on the point cloud data to be used, the object category of the point cloud data to be used in the area to be screened can be determined. If the object category includes the preset point cloud category, it means that the pit area cannot be generated based on the area to be screened, and the area to be screened can be generated again until the object category of the point cloud data to be used in the area to be screened does not include at least one preset point cloud category. The area to be screened obtained in this case is used as the area to be processed.

[0077] S230 , determining the point cloud data to be applied located in the area to be processed according to the area coordinate information of the area to be processed and the point cloud coordinate information of the point cloud data to be used.

[0078] Among them, for the area to be processed, there is a corresponding edge, and the coordinate information corresponding to the area edge can be obtained and used as the area coordinate information. The reason for determining the area coordinates is that the point cloud located in the area to be processed can be determined according to the area coordinates and the point cloud coordinate information of the point cloud data to be used, and this point cloud is used as the point cloud data to be applied.

[0079] Specifically, after obtaining the area to be processed, the area coordinate information corresponding to the area to be processed can be obtained. The area coordinate information is used as a constraint condition to determine the point cloud data within the area coordinate information range in the point cloud data to be used, and the point cloud data obtained at this time is used as the point cloud data to be applied.

[0080] On the basis of the above technical solution, after the area to be processed is determined, a three-dimensional grid model corresponding to the area to be processed can be produced.

[0081] Optionally, a three-dimensional mesh model is created based on the regional coordinate information of the area to be processed; wherein the three-dimensional mesh model is composed of multiple triangular meshes, and the attribute information of each mesh point includes the coordinates of the mesh to be processed; based on the coordinate transformation matrix between the three-dimensional mesh coordinate system and the target coordinate system, the coordinates of the mesh to be processed in the three-dimensional mesh model are processed to obtain the three-dimensional mesh model with updated attribute information; wherein the target coordinate system is the coordinate system corresponding to the acquisition of the point cloud data to be processed.

[0082] The three-dimensional mesh model can be a 3D mesh model. Assuming that the area to be processed is a rectangular area of ​​W×L, then a deep pit area of ​​W×L×H needs to be generated. A three-dimensional mesh model corresponding to the above size can be made. The three-dimensional mesh model is composed of multiple triangular meshes, each of which has three vertices, and each vertex can be composed of three coordinates of x, y, and z. Accordingly, the three-dimensional mesh model can be represented by a tensor of t×3×3. The 3D mesh model can be found in Figure 4 .

[0083] After placing the 3D mesh model in the area to be processed, the coordinates of the t×3×3 tensor can be aligned to the radar coordinate system of the original point cloud. The radar coordinate system is the target coordinate system, and the target coordinate system is the coordinate system corresponding to the point cloud data to be processed when it is collected.

[0084] The grid coordinates to be processed can be understood as the three-dimensional coordinate information of the grid points. The coordinate transformation matrix can be understood as the transformation matrix corresponding to the transformation of the grid coordinates to be processed in the 3Dmesh to the target coordinate system. The coordinates obtained after the coordinate transformation of the grid coordinates to be processed are used as the updated grid point attribute information.

[0085] S240 . For the point cloud data to be applied, based on the point cloud data to be applied and the coordinate origin of the target coordinate system, determine the target ray corresponding to the point cloud data to be applied.

[0086] Among them, the point cloud of the deep pit area can be reprojected based on Ray Tracing.

[0087] Specifically, for the point cloud data to be applied, after connecting each point cloud data to be applied and the origin of the coordinate system of the target coordinate system, the ray is extended to obtain the target point cloud data corresponding to the point cloud data to be applied in the deep pit area, and the extended ray is used as the target ray.

[0088] S250 , determining target point cloud data corresponding to the point cloud data to be applied based on the target ray and the grid point coordinates of the three-dimensional grid model located in the area to be processed.

[0089] It should be noted that the 3D grid model is composed of many grids, each grid corresponds to three grid points. Three grid points can form a plane. Based on this, the intersection point between each target and the plane formed by the grid can be found, and the point cloud data corresponding to the intersection point is used as the target point cloud data.

[0090] That is to say, after extending the target ray, the intersection point with the triangle in the above three-dimensional grid can be found, and the found intersection point is used as the target point cloud data to be applied.

[0091] On the basis of the above technical solution, after obtaining the target point cloud data, the method further includes: determining the reflectivity corresponding to the area to be processed according to the material information corresponding to the area to be processed; and updating the target point cloud data based on the reflectivity.

[0092] It can be understood that the reflectivity can be assigned to the target point cloud data in the deep pit area. The reflectivity of point clouds in the real world can be referred to. For example, the characteristics of different materials such as soil and wet cement can be used to assign new reflectivity to the point cloud data corresponding to the deep pit area. The resulting schematic diagram is as follows: Figure 5 The red part is used to represent the target point cloud data generated by the method provided by the embodiment of the present invention, and the target point cloud data is the point cloud data in the deep pit.

[0093] In this embodiment, the object category corresponding to the target point cloud data is the same as the preset object category corresponding to the pothole area.

[0094] The technical solution provided by the embodiment of the present invention can project the point cloud data to be processed after obtaining the point processing point cloud data to obtain the point cloud data to be used with the same numerical value in the first direction. Next, the area to be processed is randomly generated based on the point cloud data to be used, and the point cloud data to be applied located in the area to be processed is determined. The pothole area can be simulated, a three-dimensional grid model corresponding to the area to be processed can be created, and the three-dimensional grid model can be fused to the area to be processed. Here, according to the point cloud data to be applied and the area to be processed fused with the three-dimensional grid model, the target point cloud data corresponding to the pothole area corresponding to the area to be processed projected by each point cloud data to be applied can be determined. It is realized that the simulation-based method can efficiently and conveniently generate the target point cloud data corresponding to the preset object type, which solves the problem of high cost and low efficiency in generating the target point cloud data corresponding to the preset object type in the prior art.

[0095] The following is an embodiment of a data processing device provided by an embodiment of the present invention. The device and the method for generating target point cloud data in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the data processing device, reference can be made to the embodiment of the method for generating target point cloud data in the above embodiments.

[0096] Figure 3 This is a structural diagram of a data processing device provided by an embodiment of the present invention. The device specifically includes: a point cloud data to be used determining module 310, a point cloud data to be applied determining module 320 and a target point cloud data determining module 330.

[0097] Among them, the module for determining the point cloud data to be used 310 is used to obtain multiple point cloud data to be used by projecting multiple point cloud data to be processed, wherein the values ​​of the point cloud data to be used in the first direction are the same; the module for determining the point cloud data to be applied 320 is used to randomly generate a to-be-processed area based on the point cloud data to be used, and determine the point cloud data to be applied located in the to-be-processed area; the module for determining the target point cloud data 330 is used to determine the target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model after fusing the pre-created three-dimensional grid model corresponding to the to-be-processed area to the to-be-processed area; wherein the target point cloud data is the point cloud data corresponding to the preset object category.

[0098] On the basis of the above technical solution, the point cloud data determination module to be applied includes:

[0099] A screening area determination unit, configured to randomly generate a to-be-screened area based on the to-be-used point cloud data;

[0100] a to-be-processed area determining unit, configured to, when the object category of the to-be-screened point cloud data to be used in the to-be-screened area does not include at least one preset point cloud category, use the to-be-screened area as the to-be-processed area;

[0101] The to-be-applied point cloud data determining unit is used to determine the to-be-applied point cloud data located in the to-be-processed area according to the area coordinate information of the to-be-processed area and the point cloud coordinate information of the to-be-used point cloud data.

[0102] On the basis of the above technical solutions, the device further includes:

[0103] A mesh model creation module, used to create the three-dimensional mesh model based on the area coordinate information of the area to be processed; wherein the three-dimensional mesh model is composed of a plurality of triangular meshes, and the attribute information of each mesh point includes the coordinates of the mesh to be processed;

[0104] An attribute updating module, used for processing the to-be-processed grid coordinates in the three-dimensional grid model based on a coordinate transformation matrix between the three-dimensional grid coordinate system and the target coordinate system, to obtain a three-dimensional grid model with updated attribute information;

[0105] The target coordinate system is a coordinate system corresponding to when collecting the point cloud data to be processed.

[0106] On the basis of the above technical solutions, after the three-dimensional grid model is fused to the area to be processed, the depth of the area to be processed is the height of the three-dimensional grid model, and accordingly, the area to be processed is a three-dimensional space area.

[0107] On the basis of the above technical solutions, the target point cloud data determination module includes:

[0108] a target ray determination unit, configured to determine, for the point cloud data to be applied, a target ray corresponding to the point cloud data to be applied based on the point cloud data to be applied and a coordinate origin of a target coordinate system;

[0109] The target point cloud data determining unit is used to determine the target point cloud data corresponding to the point cloud data to be applied based on the target ray and the grid point coordinates of the three-dimensional grid model located in the area to be processed.

[0110] On the basis of the above technical solutions, the device further includes: a reflectivity assignment module, used to determine the reflectivity corresponding to the area to be processed according to the material information corresponding to the area to be processed; and update the target point cloud data based on the reflectivity.

[0111] On the basis of the above technical solutions, the object category corresponding to the target point cloud data is the same as the preset object category corresponding to the pothole area.

[0112] The technical solution provided by the embodiment of the present invention can project the point cloud data to be processed after obtaining the point processing point cloud data to obtain the point cloud data to be used with the same numerical value in the first direction. Next, the area to be processed is randomly generated based on the point cloud data to be used, and the point cloud data to be applied located in the area to be processed is determined. The pothole area can be simulated, a three-dimensional grid model corresponding to the area to be processed can be created, and the three-dimensional grid model can be fused to the area to be processed. Here, according to the point cloud data to be applied and the area to be processed fused with the three-dimensional grid model, the target point cloud data corresponding to the pothole area corresponding to the area to be processed projected by each point cloud data to be applied can be determined. It is realized that the simulation-based method can efficiently and conveniently generate the target point cloud data corresponding to the preset object type, which solves the problem of high cost and low efficiency in generating the target point cloud data corresponding to the preset object type in the prior art.

[0113] The data processing device provided in the embodiment of the present invention can execute the method for generating target point cloud data provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method for generating target point cloud data.

[0114] It is worth noting that in the embodiment of the above-mentioned data processing device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0115] Figure 7 A schematic diagram of the structure of a server provided in an embodiment of the present invention. Figure 7 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 7 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0116] like Figure 7 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0117] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0118] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0119] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0120] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0121] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0122] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the method steps for generating target point cloud data provided in the first embodiment of the present invention, the method comprising:

[0123] By projecting a plurality of point cloud data to be processed, a plurality of point cloud data to be used is obtained, wherein the values ​​of the point cloud data to be used in the first direction are the same;

[0124] Randomly generate a to-be-processed area based on the to-be-used point cloud data, and determine the to-be-applied point cloud data located in the to-be-processed area;

[0125] After fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed, determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model;

[0126] The target point cloud data is point cloud data corresponding to a preset object category.

[0127] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the method for generating target point cloud data provided by any embodiment of the present invention.

[0128] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method steps for generating target point cloud data provided by the foregoing embodiment of the present invention are implemented. The method includes:

[0129] By projecting a plurality of point cloud data to be processed, a plurality of point cloud data to be used is obtained, wherein the values ​​of the point cloud data to be used in the first direction are the same;

[0130] Randomly generate a to-be-processed area based on the to-be-used point cloud data, and determine the to-be-applied point cloud data located in the to-be-processed area;

[0131] After fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed, determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model;

[0132] The target point cloud data is point cloud data corresponding to a preset object category.

[0133] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0135] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0136] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for generating target point cloud data, characterized in that: include: By projecting a plurality of point cloud data to be processed, a plurality of point cloud data to be used is obtained, wherein the values ​​of the point cloud data to be used in the first direction are the same; Randomly generate a to-be-processed area based on the to-be-used point cloud data, and determine the to-be-applied point cloud data located in the to-be-processed area; After fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed, determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model; The target point cloud data is point cloud data corresponding to a preset object category.

2. The method according to claim 1, characterized in that: The randomly generating a to-be-processed area based on the to-be-used point cloud data, and determining the to-be-applied point cloud data located in the to-be-processed area, comprises: Randomly generate a to-be-screened area based on the to-be-used point cloud data; When the object category of the point cloud data to be used in the area to be screened does not include at least one preset point cloud category, the area to be screened is used as the area to be processed; The point cloud data to be used located in the area to be processed is determined according to the area coordinate information of the area to be processed and the point cloud coordinate information of the point cloud data to be used.

3. The method according to claim 1, characterized in that The method further comprises: Based on the area coordinate information of the area to be processed, the three-dimensional mesh model is created; wherein the three-dimensional mesh model is composed of a plurality of triangular meshes, and the attribute information of each mesh point includes the coordinates of the mesh to be processed; Processing the grid coordinates to be processed in the three-dimensional grid model based on the coordinate transformation matrix between the three-dimensional grid coordinate system and the target coordinate system to obtain a three-dimensional grid model with updated attribute information; The target coordinate system is a coordinate system corresponding to when collecting the point cloud data to be processed.

4. The method according to claim 1, characterized in that After the three-dimensional grid model is fused to the area to be processed, the depth of the area to be processed is the height of the three-dimensional grid model. Accordingly, the area to be processed is a three-dimensional space area.

5. The method according to claim 1, characterized in that The step of determining target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model includes: For the point cloud data to be applied, based on the point cloud data to be applied and the coordinate origin of the target coordinate system, determining a target ray corresponding to the point cloud data to be applied; Based on the target ray and the grid point coordinates of the three-dimensional grid model located in the area to be processed, the target point cloud data corresponding to the point cloud data to be applied is determined.

6. The method according to claim 1 or 5, characterized in that: After obtaining the target point cloud data, the method further includes: Determining the reflectivity corresponding to the area to be processed according to the material information corresponding to the area to be processed; The target point cloud data is updated based on the reflectivity.

7. The method according to claim 1, characterized in that The object category corresponding to the target point cloud data is the same as the preset object category corresponding to the pothole area.

8. A device for generating target point cloud data, characterized in that: include: a module for determining point cloud data to be used, configured to obtain a plurality of point cloud data to be used by projecting a plurality of point cloud data to be processed, wherein the values ​​of the point cloud data to be used in the first direction are the same; A module for determining point cloud data to be applied, used for randomly generating a region to be processed based on the point cloud data to be used, and determining the point cloud data to be applied located in the region to be processed; a target point cloud data determination module, configured to determine target point cloud data corresponding to the point cloud data to be applied based on the point cloud data to be applied and the three-dimensional grid model after fusing the pre-created three-dimensional grid model corresponding to the area to be processed to the area to be processed; The target point cloud data is point cloud data corresponding to a preset object category.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating target point cloud data as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for generating target point cloud data as described in any one of claims 1 to 7 is implemented.

Images