Point cloud map generation method, device, computer equipment and storage medium

Abstract

The present disclosure provides a method, device, computer equipment and storage medium for generating a point cloud map, the method comprising: obtaining point cloud maps corresponding to multiple areas of a target scene; wherein the positions indicated by some point cloud points in at least some areas of the multiple areas are the same as the positions indicated by some point cloud points in at least one other area; using the three-dimensional position information of the point cloud points indicating the same position in different areas respectively in different areas, the point cloud maps corresponding to the multiple areas are converted to a target coordinate system; based on the multiple point cloud maps converted to the target coordinate system, a target point cloud map is obtained. The embodiment of the present disclosure uses the three-dimensional position information of the point cloud points indicating the same position in different areas respectively in different areas to determine the relative position relationship between the point cloud maps of different areas, and realizes the splicing of different point cloud maps, which has higher accuracy and generation efficiency than the manual splicing method.

Description

Technical Field

[0001] The present disclosure relates to the field of computer vision technology, and in particular to a method, device, computer equipment and storage medium for generating a point cloud map. Background Art

[0002] At present, point cloud maps are usually used to express scene information in the fields of augmented reality (AR) navigation and AR games. Point cloud maps usually include multiple point cloud points with semantic information and the three-dimensional position information of each point cloud point in the world coordinate system; these point cloud points can indicate the specific distribution of different objects in space in a certain scene. The current point cloud map generation method has the problems of low accuracy and low generation efficiency. Summary of the invention

[0003] The embodiments of the present disclosure at least provide a method, apparatus, computer equipment and storage medium for generating a point cloud map.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for generating a point cloud map, comprising: obtaining point cloud maps corresponding to multiple areas of a target scene, respectively; wherein positions indicated by some point cloud points in at least some areas of the multiple areas are the same as positions indicated by some point cloud points in at least one other area; converting the point cloud maps corresponding to the multiple areas into a target coordinate system using three-dimensional position information of point cloud points indicating the same positions in different areas, respectively, in the different areas; and obtaining a target point cloud map based on the multiple point cloud maps converted into the target coordinate system.

[0005] In this way, the three-dimensional position information of point cloud points indicating the same position in different areas can be used to determine the relative position relationship between point cloud maps of different areas, and then the splicing of different point cloud maps can be achieved based on the relative position relationship, which has higher accuracy and generation efficiency than manual splicing.

[0006] In an optional implementation, positions indicated by some of the point cloud points in each of the multiple areas are the same as positions indicated by some of the point cloud points in at least one other area.

[0007] In an optional implementation, positions indicated by some point cloud points in every two adjacent areas of the multiple areas are the same.

[0008] In an optional embodiment, the three-dimensional position information of the point cloud points indicating the same position in different areas is used to convert the point cloud maps corresponding to the different areas to the target coordinate system, including: taking any point cloud map among the multiple point cloud maps as the first point cloud map, and determining a first transformation matrix between the first area coordinate system corresponding to the first point cloud map and the target coordinate system, and using the first transformation matrix to convert the first point cloud map to the target coordinate system; performing the following conversion process until all the first point cloud maps are converted to the target coordinate system; the conversion process includes: determining A second point cloud map; the second point cloud map includes second point cloud points, and the second point cloud points have the same position as the first point cloud points included in the first point cloud map; using the three-dimensional position information of the first point cloud points in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud points in the second point cloud map in the second regional coordinate system, determine a second transformation matrix between the second regional coordinate system and the target coordinate system, and use the second transformation matrix to transform the second point cloud map to the target coordinate system; use the second point cloud map as the new first point cloud map, and return to the step of determining the second point cloud map.

[0009] In this way, through the above process, the point cloud maps in different coordinate systems can be converted into a unified coordinate system.

[0010] In an optional embodiment, converting the second point cloud map to the target coordinate system includes: using the second transformation matrix to convert the three-dimensional position information of each point cloud point in the first point cloud map in the first area coordinate system into the three-dimensional position information in the target coordinate system, so as to convert the second point cloud map to the target coordinate system.

[0011] In an optional implementation, the target coordinate system includes any one of the following: a randomly determined coordinate system; or a regional coordinate system corresponding to any point cloud map.

[0012] In an optional implementation, different areas include different floors of the target scene.

[0013] In an optional implementation, obtaining the target point cloud map based on the point cloud maps converted to the target coordinate system includes: fusing the multiple point cloud maps converted to the target coordinate system to obtain the target point cloud map.

[0014] In an optional implementation, the generation method further includes: determining point cloud points indicating the same location in different point cloud maps.

[0015] In a second aspect, an embodiment of the present disclosure also provides a device for generating a point cloud map, comprising: an acquisition module, used to acquire point cloud maps corresponding to multiple areas of a target scene, respectively; wherein the positions indicated by some point cloud points in at least some of the multiple areas are the same as the positions indicated by some point cloud points in at least one other area; a conversion module, used to convert the point cloud maps corresponding to the multiple areas into a target coordinate system by using three-dimensional position information of point cloud points indicating the same positions in different areas, respectively, in the different areas; a first determination module, used to obtain a target point cloud map based on the multiple point cloud maps converted to the target coordinate system.

[0016] In an optional implementation, positions indicated by some of the point cloud points in each of the multiple areas are the same as positions indicated by some of the point cloud points in at least one other area.

[0017] In an optional implementation, positions indicated by some point cloud points in every two adjacent areas of the multiple areas are the same.

[0018] In an optional embodiment, when the conversion module uses the three-dimensional position information of the point cloud points indicating the same position in different areas to convert the point cloud maps corresponding to the different areas to the target coordinate system, it is used to: use any point cloud map among the multiple point cloud maps as the first point cloud map, and determine a first conversion matrix between the first area coordinate system corresponding to the first point cloud map and the target coordinate system, and use the first conversion matrix to convert the first point cloud map to the target coordinate system; perform the following conversion process until all the first point cloud maps are converted to the target coordinate system; the conversion process includes : Determine a second point cloud map; the second point cloud map includes a second point cloud point, and the second point cloud point has the same position as the first point cloud point included in the first point cloud map; use the three-dimensional position information of the first point cloud point in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud point in the second point cloud map in the second regional coordinate system to determine a second transformation matrix between the second regional coordinate system and the target coordinate system, and use the second transformation matrix to transform the second point cloud map to the target coordinate system; use the second point cloud map as the new first point cloud map, and return to the step of determining the second point cloud map.

[0019] In an optional embodiment, when converting the second point cloud map to the target coordinate system, the conversion module is used to: use the second transformation matrix to convert the three-dimensional position information of each point cloud point in the first point cloud map in the first area coordinate system into the three-dimensional position information in the target coordinate system, so as to convert the second point cloud map to the target coordinate system.

[0020] In an optional implementation, the target coordinate system includes any one of the following: a randomly determined coordinate system; or a regional coordinate system corresponding to any point cloud map.

[0021] In an optional implementation, different areas include different floors of the target scene.

[0022] In an optional embodiment, when obtaining the target point cloud map based on the point cloud maps converted to the target coordinate system, the first determination module is used to: fuse the multiple point cloud maps converted to the target coordinate system to obtain the target point cloud map.

[0023] In an optional implementation, the generating device further includes a second determining module, configured to determine point cloud points indicating the same location in different point cloud maps.

[0024] In a third aspect, an optional implementation of the present disclosure further provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the machine-readable instructions perform the steps of the above-mentioned first aspect, or any possible implementation of the first aspect.

[0025] In a fourth aspect, an optional implementation of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the above-mentioned first aspect, or any possible implementation of the first aspect are executed.

[0026] For a description of the effects of the above-mentioned point cloud map generation device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned point cloud map generation method, which will not be repeated here.

[0027] The point cloud map generation method, device, computer equipment and storage medium provided by the embodiments of the present disclosure obtain the point cloud map of each of the multiple areas of the target scene, and based on the three-dimensional position information of the point cloud points indicating the same position in the different areas, respectively, the point cloud maps corresponding to the different areas are converted to the target coordinate system, and based on the multiple point cloud maps converted to the target coordinate system, the target point cloud map is obtained. Since the three-dimensional position information of the point cloud points indicating the same position in different areas in different areas can determine the mutual position relationship between the point cloud maps of different areas, and then based on the mutual position relationship, the splicing of different point cloud maps can be achieved, which has higher accuracy and generation efficiency than the manual splicing method.

[0028] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0030] Figure 1 A flow chart of a method for generating a point cloud map provided by an embodiment of the present disclosure is shown;

[0031] Figure 2 A schematic diagram of a point cloud map generation device provided by an embodiment of the present disclosure is shown;

[0032] Figure 3 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0034] Research has found that in order to obtain a point cloud map of a target scene with a large spatial range, it is usually necessary to collect point cloud data for different areas in the target scene respectively; then, the collection results of the point cloud data corresponding to each area are used to form a point cloud map corresponding to the area; then, the point cloud maps corresponding to different areas are spliced ​​together by manual alignment to form a point cloud map of the target scene; this method of generating point cloud maps requires manual splicing, which is prone to errors caused by human factors, and therefore has the problem of low accuracy; at the same time, the manual splicing method also causes the problem of low generation efficiency.

[0035] Based on the above research, the present disclosure provides a method, device, computer equipment and storage medium for generating a point cloud map. The three-dimensional position information of point cloud points indicating the same position in different areas can be used to determine the relative position relationship between point cloud maps of different areas. Based on the relative position relationship, the splicing of different point cloud maps can be achieved, which has higher accuracy and generation efficiency than manual splicing.

[0036] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0037] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0038] To facilitate understanding of this embodiment, a method for generating a point cloud map disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the method for generating a point cloud map provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method for generating a point cloud map can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0039] The following is an explanation of the method for generating a point cloud map provided in an embodiment of the present disclosure.

[0040] See also Figure 1 FIG. 1 is a flowchart of a method for generating a point cloud map provided by an embodiment of the present disclosure, the method comprising steps S101 to S103, wherein:

[0041] S101: Obtaining point cloud maps corresponding to multiple areas of a target scene, respectively; wherein positions indicated by some point cloud points in at least some areas of the multiple areas are the same as positions indicated by some point cloud points in at least one other area;

[0042] S102: using the three-dimensional position information of the point cloud points indicating the same position in different areas in different areas, respectively, to convert the point cloud maps corresponding to the different areas into the target coordinate system;

[0043] S103: Obtain a target point cloud map based on the multiple point cloud maps converted to the target coordinate system.

[0044] The disclosed embodiment obtains a point cloud map of each of the multiple regions of the target scene, and based on the three-dimensional position information of the point cloud points indicating the same position in different regions, respectively, the point cloud maps corresponding to the different regions are converted to the target coordinate system, and based on the multiple points and maps converted to the target coordinate system, a target point cloud map is obtained. Since the three-dimensional position information of the point cloud points indicating the same position in different regions respectively in different regions can determine the mutual position relationship between the point cloud maps of different regions, then based on the mutual position relationship, the splicing of different point cloud maps can be achieved, which has higher accuracy and generation efficiency than the manual splicing method.

[0045] The above S101 to S103 are described in detail below.

[0046] With respect to the above S101, illustratively, the target scene may include, for example, a shopping mall with multiple floors, a duplex house with a loft, and other buildings with multiple floors; for another example, the target scene may also include a place with a large undulating terrain, such as a scenic spot with mountains; the multiple areas in the target scene may be set according to actual conditions, for example, each floor of the shopping mall may be determined as an area; or each of the multiple rooms in the duplex house with a loft may be determined as an area.

[0047] The point cloud map corresponding to each area is a point cloud map established for multiple areas respectively, and since the point cloud maps of different areas are established respectively, the coordinate systems corresponding to different point cloud maps are different.

[0048] The point cloud map of each region includes multiple point cloud points. Each point cloud point indicates a certain position in the region; the position is usually the spatial position of the key point of the object in the region.

[0049] Exemplarily, the embodiment of the present disclosure further provides a specific method for obtaining a point cloud map corresponding to each of a plurality of areas in a target scene, the method comprising:

[0050] A video of each area in a target scene captured by an image acquisition device is obtained; the video includes multiple video frame images; based on the video, the three-dimensional coordinate values ​​of the key points of each object in each area in the regional coordinate system corresponding to each area are determined; based on the three-dimensional coordinate values ​​of the key points of each object in each area in the regional coordinate system corresponding to each area, a point cloud map corresponding to each area is generated.

[0051] In a specific implementation, an image acquisition device is used to acquire images of each area in the target scene. During the image acquisition process, a video corresponding to each area is obtained; each video includes a video frame image of the object in the area. In addition, for different areas with adjacent positional relationships, when using an image acquisition device to acquire images, it is necessary to acquire video frame images that include some objects in the adjacent areas. Therefore, in the point cloud map corresponding to each generated area, some point cloud points will be included, and the position in the target scene indicated by the some point cloud points is the same as the position indicated by some point cloud points in the point cloud map corresponding to at least another other area.

[0052] That is, the positions indicated by some of the point cloud points in each of the multiple regions are the same as the positions indicated by some of the point cloud points in at least one other region, wherein the positions indicated by some of the point cloud points in every two adjacent regions in the multiple regions are the same.

[0053] The image acquisition device includes, for example, at least one of a depth camera and a color camera.

[0054] In the case where the image acquisition device includes a depth camera, the depth camera may utilize one or more of structured light, binocular vision, light time-of-flight method, etc. when acquiring a video of a target scene.

[0055] In the case where the image acquisition device includes a depth camera, a regional coordinate system can be established based on the starting point of video acquisition. The moving angle between each two video frames of the depth camera during the video acquisition process can be detected by a gyroscope installed in the depth camera, or by identifying and matching key points of the two acquired video frames, and determining it based on the matching results; the moving distance of the depth camera during the video acquisition process can also be determined by identifying and matching key points of the two acquired video frames, and determining it based on the matching results. Based on the moving angle, moving distance, and depth values ​​of key points in each video frame of the depth camera, the three-dimensional coordinate values ​​of the point cloud points corresponding to each key point in the regional coordinate system can be determined.

[0056] In the case where the image acquisition device includes a color camera, for example, any one of Simultaneous Localization and Mapping (SLAM) modeling and Structure-From-Motion (SFM) modeling can be used, and based on the video acquired by the color camera, the three-dimensional coordinate values ​​of the key points of each object in each area in the regional coordinate system corresponding to each area can be determined.

[0057] After obtaining the three-dimensional coordinate values ​​of the key points of each object in the area under the regional coordinates corresponding to each area, the point cloud points corresponding to the key points are determined based on the key points, and the three-dimensional coordinate values ​​of the key points are determined as the three-dimensional coordinate values ​​of the corresponding point cloud points to generate a point cloud map composed of point cloud points.

[0058] In another embodiment, after the point cloud points corresponding to each key point are determined, due to certain errors that may exist in the process of image processing, a large deviation may occur in the position of the key point in the scene coordinate system; in order to reduce the impact of the deviation on the accuracy of the point cloud map, the point cloud points corresponding to each key point can be used as original point cloud points, and the original point cloud points are subjected to at least one of filtering processing, denoising processing, and outlier removal processing to obtain a point cloud map corresponding to the area.

[0059] Through the above process, based on the three-dimensional coordinate values ​​of the key points of each object in each area in the regional coordinate system corresponding to each area, and the regional coordinate system corresponding to each area, the position information of the point cloud points corresponding to each area in the point cloud map corresponding to the area can be determined, thereby generating a point cloud map corresponding to each area.

[0060] For the above S102, when the point cloud maps corresponding to the areas are converted to the target coordinate system by using the three-dimensional position information of the point cloud points indicating the same position in different areas respectively in different areas, the relative position relationship between the different point cloud maps is determined by using the three-dimensional position information of the point cloud points indicating the same position in different areas respectively in different areas, and based on the relative position relationship, the different point cloud maps are spliced ​​into a target point cloud map.

[0061] Exemplarily, an embodiment of the present disclosure provides a specific method for converting point cloud maps corresponding to different areas into a target coordinate system by using three-dimensional position information of point cloud points indicating the same position in different areas in the different areas, including:

[0062] Any point cloud map among the multiple point cloud maps is used as a first point cloud map, and a first transformation matrix between a first regional coordinate system corresponding to the first point cloud map and a target coordinate system is determined, and the first point cloud map is transformed into the target coordinate system using the first transformation matrix; the following transformation process is performed until all the first point cloud maps are transformed into the target coordinate system; the transformation process includes:

[0063] Determine a second point cloud map; the second point cloud map includes a second point cloud point, and the second point cloud point has the same position as the first point cloud point included in the first point cloud map; use the three-dimensional position information of the first point cloud point in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud point in the second point cloud map in the second regional coordinate system to determine a second transformation matrix between the second regional coordinate system and the target coordinate system, and use the second transformation matrix to transform the second point cloud map to the target coordinate system; use the second point cloud map as the new first point cloud map, and return to the step of determining the second point cloud map.

[0064] In a specific implementation, in a possible implementation manner, a point cloud map is selected from multiple point cloud maps as a first point cloud map, and a transformation matrix between a first area coordinate system corresponding to the first point cloud map and a target coordinate system is obtained.

[0065] For example, A i (i=1,2,…n) represents the i-th point cloud map, where n represents the number of point cloud maps.

[0066] For example, the first point cloud map A1 is first determined as the first point cloud map, and the target coordinate system O is determined. Wherein, O can be a randomly determined coordinate system, or the target coordinate system O can be a regional coordinate system corresponding to the first point cloud map A1.

[0067] In the embodiment of the present disclosure, taking a randomly determined coordinate system as the target coordinate system as an example, since O is randomly determined, that is, the origin, x-axis, y-axis, and z-axis of the regional coordinate system corresponding to the first point cloud map A1 are known, the origin, x-axis, y-axis, and z-axis of the target coordinate system O are also known, and thus the first transformation matrix between the first point cloud map A1 and the target coordinate system O can be established.

[0068] by Represents the 3D coordinate value of the point cloud point in the i-th point cloud map. For example, when i is 1, represents the three-dimensional coordinate value of the point cloud point in the first point cloud map A1; when any point cloud map is obtained from multiple point cloud maps as the first point cloud map A1, the three-dimensional coordinate value of the point cloud point in the first point cloud map A1 is expressed as

[0069] When obtaining the conversion matrix between the first area coordinate system corresponding to the first point cloud map A1 and the target coordinate system O, the conversion matrix is ​​expressed as The matrix conversion models that can be used include at least one of the following: Bursa model, Molochinsky model and paradigm model.

[0070] Based on the transformation matrix and the three-dimensional coordinate values ​​of each point cloud point in the first point cloud map It is possible to determine the three-dimensional coordinate values ​​of each point cloud point in the first point cloud map converted to the target coordinate system This realizes the conversion of the first point cloud map to the target coordinate system O.

[0071] Determine that the point cloud map A2 contains the point cloud points indicating the same position as the first point cloud map A1, and use A2 as the second point cloud map; wherein the three-dimensional coordinate values ​​of the point cloud points in the second point cloud map A2 are expressed as Since the first point cloud point in the first point cloud map A1 and the point cloud point indicating the same position in the second point cloud map A2 can be determined in advance, the point cloud point indicating the same position in the first point cloud map A1 is the first point cloud point, and the point cloud point indicating the same position in the second point cloud map A2 is the second point cloud point, which are respectively represented as P1 and P2.

[0072] Among them, the three-dimensional coordinate value of P1 in the target coordinate is expressed as: The three-dimensional coordinate value of P2 in the second scene coordinate system where the second point cloud map is located is expressed as: based on and A second transformation matrix between the second area coordinate system and the target coordinate system O can be determined

[0073] Based on the three-dimensional coordinate values ​​of the point cloud points in the second point cloud map A2 and a second transformation matrix between the second regional coordinate system and the target coordinate system O Convert the three-dimensional coordinate values ​​of each point cloud point in the second point cloud map in the second scene coordinate system to the three-dimensional coordinate values ​​in the target coordinate system O Thereby, the second point cloud map A2 is converted into the target coordinate system O.

[0074] The second point cloud map A2 is used as the new first point cloud map. Assuming that at this time, the other point cloud map with the same point cloud point pointing to the same position as A2 is A3, A3 is used as the new second point cloud map, and the process returns to the step of determining the second point cloud map. Repeat the above steps until all point cloud maps are converted to the target coordinate system O.

[0075] Regarding the above S103: when obtaining the target point cloud map based on the point cloud maps converted to the target coordinate system, multiple point cloud points converted to the target coordinate system are merged into the target coordinate system to form a total point cloud map including all point cloud maps.

[0076] Exemplarily, for example, the plurality of point cloud maps converted into the target coordinate system may be fused to obtain the target point cloud map.

[0077] In the point cloud maps A corresponding to the different areas i After conversion to the target coordinate system O, the multiple point cloud maps converted to the target coordinate system are fused to obtain the target point cloud map, and it is necessary to merge the repeated point cloud points indicating the same position.

[0078] In a possible implementation, the point cloud maps are spliced ​​at corresponding positions in the target coordinate system using the first point cloud point in the point cloud map converted from the first point cloud map to the target coordinate system and the second point cloud point in the point cloud map converted from the second point cloud map to the target coordinate system, until the splicing of all point cloud maps converted to the target coordinate system is completed to obtain the target point cloud map.

[0079] In another possible implementation, all the point cloud maps A are obtained. i The three-dimensional coordinate value of the corresponding point cloud point And the transformation matrix between all the point cloud maps and the target coordinate system O The point cloud point positions indicated by the three-dimensional coordinate values ​​of the point cloud points in all the point cloud maps in the target coordinate system are determined to obtain a target point cloud map.

[0080] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0081] Based on the same inventive concept, the embodiment of the present disclosure also provides a point cloud map generation device corresponding to the point cloud map generation method. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned point cloud map generation method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0082] Reference Figure 2 , which is a schematic diagram of a device for generating a point cloud map provided by an embodiment of the present disclosure, the device comprises: an acquisition module 21, a conversion module 22, and a first determination module 23; wherein,

[0083] An acquisition module 21 is used to acquire point cloud maps corresponding to a plurality of regions of a target scene, wherein positions indicated by some point cloud points in at least some of the plurality of regions are the same as positions indicated by some point cloud points in at least one other region;

[0084] A conversion module 22, configured to convert the point cloud maps corresponding to the plurality of regions into a target coordinate system by using the three-dimensional position information of the point cloud points indicating the same position in the different regions in the different regions;

[0085] The first determination module 23 is used to obtain a target point cloud map based on the multiple point cloud maps converted into the target coordinate system.

[0086] In an optional implementation, positions indicated by some of the point cloud points in each of the multiple areas are the same as positions indicated by some of the point cloud points in at least one other area.

[0087] In an optional implementation, positions indicated by some point cloud points in every two adjacent areas of the multiple areas are the same.

[0088] In an optional embodiment, the conversion module 22, when using the three-dimensional position information of the point cloud points indicating the same position in different areas respectively in the different areas, converts the point cloud maps corresponding to the different areas to the target coordinate system, is used to: use any point cloud map among the multiple point cloud maps as the first point cloud map, and determine a first conversion matrix between the first area coordinate system corresponding to the first point cloud map and the target coordinate system, and use the first conversion matrix to convert the first point cloud map to the target coordinate system; perform the following conversion process until all the first point cloud maps are converted to the target coordinate system; the conversion process includes The method comprises: determining a second point cloud map; the second point cloud map comprises a second point cloud point, and the second point cloud point has the same position as that indicated by the first point cloud point included in the first point cloud map; determining a second transformation matrix between the second regional coordinate system and the target coordinate system using the three-dimensional position information of the first point cloud point in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud point in the second point cloud map in the second regional coordinate system, and transforming the second point cloud map to the target coordinate system using the second transformation matrix; using the second point cloud map as the new first point cloud map, and returning to the step of determining the second point cloud map.

[0089] In an optional embodiment, when converting the second point cloud map to the target coordinate system, the conversion module 22 is used to: use the second transformation matrix to convert the three-dimensional position information of each point cloud point in the first point cloud map in the first area coordinate system into the three-dimensional position information in the target coordinate system, so as to convert the second point cloud map to the target coordinate system.

[0090] In an optional implementation, the target coordinate system includes any one of the following: a randomly determined coordinate system; or a regional coordinate system corresponding to any point cloud map.

[0091] In an optional implementation, different areas include different floors of the target scene.

[0092] In an optional embodiment, when obtaining the target point cloud map based on the point cloud maps converted to the target coordinate system, the first determination module 23 is used to: fuse the multiple point cloud maps converted to the target coordinate system to obtain the target point cloud map.

[0093] In an optional implementation, the generating device further includes a second determining module 24, which is used to determine point cloud points indicating the same position in different point cloud maps.

[0094] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0095] The present disclosure also provides a computer device, such as Figure 3 FIG. 1 is a schematic diagram of a computer device structure provided in an embodiment of the present disclosure, including:

[0096] A processor 31 and a memory 32; the memory 32 stores machine-readable instructions executable by the processor 31, and the processor 31 is used to execute the machine-readable instructions stored in the memory 32. When the machine-readable instructions are executed by the processor 31, the processor 31 performs the following steps:

[0097] Obtain point cloud maps corresponding to multiple areas of the target scene; wherein the positions indicated by some point cloud points in at least some areas of the multiple areas are the same as the positions indicated by some point cloud points in at least one other area; convert the point cloud maps corresponding to the multiple areas to a target coordinate system using the three-dimensional position information of point cloud points indicating the same positions in different areas; obtain a target point cloud map based on the multiple point cloud maps converted to the target coordinate system.

[0098] The above-mentioned memory 32 includes internal memory 321 and external memory 322; the memory 321 here is also called internal memory, which is used to temporarily store the calculation data in the processor 31, as well as the data exchanged with the external memory 322 such as the hard disk. The processor 31 exchanges data with the external memory 322 through the internal memory 321.

[0099] The specific execution process of the above instructions can refer to the steps of the method for generating a point cloud map described in the embodiment of the present disclosure, which will not be repeated here.

[0100] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for generating a point cloud map described in the above method embodiment are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0101] The present disclosure also provides a computer program product that carries a program code. The program code includes instructions that can be used to execute the steps of the method for generating a point cloud map described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0102] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0103] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, 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, which is stored in a storage medium and includes several 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 disclosure. 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 magnetic disk or an optical disk.

[0107] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for generating a point cloud map, characterized in that: include: Obtaining point cloud maps corresponding to a plurality of regions of the target scene, respectively; wherein positions indicated by some of the point cloud points in at least some of the plurality of regions are the same as positions indicated by some of the point cloud points in at least one other region; Using the three-dimensional position information of the point cloud points indicating the same position in different areas in the different areas, respectively, the point cloud maps corresponding to the multiple areas are converted to the target coordinate system; Based on the plurality of point cloud maps converted into the target coordinate system, a target point cloud map is obtained; The method of using the three-dimensional position information of the point cloud points indicating the same position in different areas to convert the point cloud maps corresponding to the multiple areas to the target coordinate system includes: Taking any point cloud map among the multiple point cloud maps as a first point cloud map, determining a first transformation matrix between a first regional coordinate system corresponding to the first point cloud map and a target coordinate system, and using the first transformation matrix to transform the first point cloud map to the target coordinate system; The following conversion process is performed until all first point cloud maps are converted to the target coordinates; the conversion process includes: Determine a second point cloud map; the second point cloud map includes a second point cloud point, and the second point cloud point is at the same position as the first point cloud point included in the first point cloud map; Determine a second transformation matrix between the second regional coordinate system and the target coordinate system using the three-dimensional position information of the first point cloud point in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud point in the second point cloud map in the second regional coordinate system, and transform the second point cloud map to the target coordinate system using the second transformation matrix; The second point cloud map is used as a new first point cloud map, and the process returns to the step of determining the second point cloud map.

2. The generation method according to claim 1, characterized in that: A position indicated by some of the point cloud points in each of the multiple regions is the same as a position indicated by some of the point cloud points in at least one other region.

3. The generation method according to claim 1 or 2, characterized in that: Positions indicated by some of the point cloud points in every two adjacent areas of the multiple areas are the same.

4. The generation method according to claim 1, characterized in that: The converting the second point cloud map to the target coordinate system includes: The second transformation matrix is ​​used to transform the three-dimensional position information of each point cloud point in the first point cloud map in the first regional coordinate system into the three-dimensional position information in the target coordinate system, so as to transform the second point cloud map into the target coordinate system.

5. The generation method according to claim 1, characterized in that: The target coordinate system includes any of the following: Randomly determined coordinate system; The regional coordinate system corresponding to any point cloud map.

6. The generation method according to claim 1, characterized in that: Different areas include different floors of the target scene.

7. The generation method according to claim 1, characterized in that: The step of obtaining a target point cloud map based on each point cloud map converted to the target coordinate system includes: The multiple point cloud maps converted into the target coordinate system are fused to obtain the target point cloud map.

8. The generation method according to claim 1, characterized in that Also includes: Identify point cloud points that indicate the same location in different point cloud maps.

9. A device for generating a point cloud map, characterized in that: include: An acquisition module, used to acquire point cloud maps corresponding to a plurality of regions of a target scene, respectively; wherein positions indicated by some point cloud points in at least some of the plurality of regions are the same as positions indicated by some point cloud points in at least one other region; A conversion module, used to convert the point cloud maps corresponding to the multiple areas into a target coordinate system by using the three-dimensional position information of the point cloud points indicating the same position in different areas in the different areas; A first determining module, configured to obtain a target point cloud map based on the plurality of point cloud maps converted into the target coordinate system; The conversion module, when converting the point cloud maps corresponding to the plurality of regions respectively into the target coordinate system by using the three-dimensional position information of the point cloud points indicating the same position in the different regions respectively in the different regions, is used to: Taking any point cloud map among the multiple point cloud maps as a first point cloud map, determining a first transformation matrix between a first regional coordinate system corresponding to the first point cloud map and a target coordinate system, and using the first transformation matrix to transform the first point cloud map to the target coordinate system; The following conversion process is performed until all first point cloud maps are converted to the target coordinates; the conversion process includes: Determine a second point cloud map; the second point cloud map includes a second point cloud point, and the second point cloud point is at the same position as the first point cloud point included in the first point cloud map; Determine a second transformation matrix between the second regional coordinate system and the target coordinate system using the three-dimensional position information of the first point cloud point in the first point cloud map in the target coordinate system and the three-dimensional position information of the second point cloud point in the second point cloud map in the second regional coordinate system, and transform the second point cloud map to the target coordinate system using the second transformation matrix; The second point cloud map is used as a new first point cloud map, and the process returns to the step of determining the second point cloud map.

10. A computer device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the processor executes the steps of the method for generating a point cloud map as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program. When the computer program is executed by a computer device, the computer device executes the steps of the method for generating a point cloud map according to any one of claims 1 to 8.

Images