House point cloud segmentation method and device

Abstract

The invention relates to a house point cloud segmentation method and device. The method comprises the following steps: obtaining initial point cloud data corresponding to a target building and a building image, determining spatial position information of a target frame in a point cloud space corresponding to the initial point cloud data according to the building image, and performing point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain a point cloud segmentation result; and obtaining building point cloud data corresponding to the target building, the target frame being a position frame corresponding to the target building in the building image. By adopting the method, the point cloud segmentation efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of point cloud data processing, and in particular to a method and device for house point cloud segmentation. Background Art

[0002] Point clouds are collections of three-dimensional spatial data acquired through technologies such as lidar, photogrammetry, and 3D scanners. In the field of architecture, point cloud technology can quickly obtain a three-dimensional "digital twin" of the building as a whole and its details, avoiding manual measurement errors. However, the point cloud data of the target building acquired using existing technologies usually contains multiple objects such as other houses, trees, the ground, and vehicles. Therefore, point cloud segmentation is required for the point cloud data corresponding to the target building.

[0003] Traditional point cloud segmentation methods usually involve manually segmenting the point cloud data of the target building from other interfering point cloud data.

[0004] However, the above point cloud segmentation methods have the problem of low segmentation efficiency. Summary of the Invention

[0005] Based on this, it is necessary to provide a house point cloud segmentation method and device that can segment efficiently in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for segmenting a house point cloud, comprising:

[0007] Obtain the initial point cloud data and building image corresponding to the target building;

[0008] According to the building image, determining the spatial position information of the target frame in the point cloud space corresponding to the initial point cloud data, where the target frame is the position frame corresponding to the target building in the building image;

[0009] The initial point cloud data is segmented according to the spatial position information to obtain the building point cloud data corresponding to the target building.

[0010] In one embodiment, determining spatial position information of a target frame in a point cloud space corresponding to initial point cloud data based on a building image includes:

[0011] According to the building image, determining the plane position information of the target frame in the building image;

[0012] The spatial position information is determined based on the planar position information.

[0013] In one embodiment, determining the spatial position information based on the planar position information includes:

[0014] Get the IMU data corresponding to the target building;

[0015] According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

[0016] In one embodiment, determining the planar position information of the target frame in the building image according to the building image includes:

[0017] Perform target detection processing on building images to obtain plane position information.

[0018] In one embodiment, performing point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building includes:

[0019] Determine the point cloud segmentation path based on spatial position information;

[0020] The initial point cloud data is segmented according to the point cloud segmentation path to obtain building point cloud data.

[0021] In one embodiment, determining a point cloud segmentation path according to spatial position information includes:

[0022] Fit the spatial position information with the point cloud plane corresponding to the initial point cloud data to obtain the normal vector corresponding to the target frame;

[0023] The point cloud segmentation path is determined based on the spatial position information and normal vector.

[0024] In a second aspect, the present application further provides a house point cloud segmentation device, comprising:

[0025] An acquisition module is used to obtain the initial point cloud data and building images corresponding to the target building;

[0026] A target frame position determination module is used to determine the spatial position information of the target frame in the point cloud space corresponding to the initial point cloud data based on the building image, where the target frame is a position frame corresponding to the target building in the building image;

[0027] The segmentation module is used to perform point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain the building point cloud data corresponding to the target building.

[0028] In a third aspect, an embodiment of the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the first aspect described above when the computer program is executed by a processor.

[0030] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method in the first aspect.

[0031] The above-mentioned house point cloud segmentation method and device, by obtaining the initial point cloud data corresponding to the target building and the building image, can determine the spatial position information of the target frame in the point cloud space corresponding to the initial point cloud data based on the building image, thereby performing point cloud segmentation processing on the initial point cloud data based on the spatial position information to obtain the building point cloud data corresponding to the target building, wherein the target frame is the position frame corresponding to the target building in the building image. In this way, the spatial position information of the target frame corresponding to the target building in the point cloud space is determined by the building image, and the initial point cloud data is subjected to point cloud segmentation processing using the spatial position information, thereby automatically removing the point cloud data causing interference in the initial point cloud data, and obtaining the building point cloud data corresponding to the target building. This avoids the problem of low segmentation efficiency existing in traditional point cloud segmentation technologies through manual point cloud segmentation. The technical solution provided by this application can realize automatic point cloud segmentation and improve segmentation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1-a A diagram showing an application environment of a house point cloud segmentation method according to an embodiment;

[0034] Figure 1-b is a system structure diagram of a server in one embodiment;

[0035] Figure 2 1 is a flow chart of a method for segmenting a house point cloud according to an embodiment;

[0036] Figure 3 202 is a flow chart of step 202 in another embodiment;

[0037] Figure 4 is a schematic flow chart of step 203 in another embodiment;

[0038] Figure 5 1 is a flow chart of an exemplary method for segmenting a house point cloud in one embodiment;

[0039] Figure 6 1. It is a structural block diagram of a house point cloud segmentation device in one embodiment;

[0040] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0042] Point clouds are collections of three-dimensional spatial data acquired through technologies such as lidar, photogrammetry, and 3D scanners. In the field of architecture, point cloud technology can quickly obtain a three-dimensional "digital twin" of the building as a whole and its details, avoiding manual measurement errors. However, the point cloud data of the target building acquired using existing technologies usually contains multiple objects such as other houses, trees, the ground, and vehicles. Therefore, point cloud segmentation is required for the point cloud data corresponding to the target building.

[0043] Traditional point cloud segmentation methods usually involve manually segmenting the point cloud data of the target building from other interfering point cloud data. However, point cloud data usually contains a large number of points. Especially when processing point clouds of large-scale scenes such as urban terrain and large buildings, the data volume may reach millions or even billions of points. Manual point cloud segmentation requires analysis and judgment point by point or area by area, which consumes a lot of time and energy and has the problem of low segmentation efficiency.

[0044] In view of this, the present application provides a cloud segmentation method, apparatus, device, readable storage medium, and program product. By acquiring initial point cloud data and a building image corresponding to a target building, the spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data can be determined based on the building image, thereby performing point cloud segmentation processing on the initial point cloud data based on the spatial position information to obtain building point cloud data corresponding to the target building, wherein the target frame is a position frame corresponding to the target building in the building image. In this way, the spatial position information of the target frame corresponding to the target building in the point cloud space is determined based on the building image, and the initial point cloud data is subjected to point cloud segmentation processing using the spatial position information, thereby automatically removing the point cloud data that causes interference in the initial point cloud data, and obtaining the building point cloud data corresponding to the target building. This avoids the problem of low segmentation efficiency in traditional point cloud segmentation techniques that exist through manual point cloud segmentation. The technical solution provided by the present application can realize automated point cloud segmentation and improve segmentation efficiency.

[0045] The house point cloud segmentation method provided in the embodiment of the present application can be applied to Figure 1-a In the application environment shown, the data storage system can store data that server 101 needs to process. The data storage system can be integrated on server 101, or it can be placed on the cloud or other network servers. Server 101 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] Reference Figure 1-b The server 101 is connected to a variety of devices (either wired or wireless), including an image acquisition device and a point cloud data acquisition device. The image acquisition device can be used to acquire images of a target building from multiple directions. The image acquisition device can be a full-frame camera. The point cloud data acquisition device is used to acquire initial point cloud data of building point cloud data corresponding to the target building. The point cloud data acquisition device includes a fisheye camera and an IMU (Inertial Measurement Unit). The laser radar can be used to scan the target building to obtain initial point cloud data including building point cloud data corresponding to the target building. The fisheye camera can collect relevant image information and cooperate with the laser radar to colorize the initial point cloud data. In this embodiment of the present application, the point cloud data acquisition device and the image acquisition device can belong to the same acquisition device. Therefore, the IMU can acquire IMU data corresponding to the acquisition device. The IMU data can reflect the motion information of the acquisition device when acquiring the building image and the initial point cloud data. The power supply unit can power the acquisition device.

[0047] In an exemplary embodiment, Figure 2 As shown, a house point cloud segmentation method is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps 201 to 203. Among them:

[0048] Step 201: Acquire initial point cloud data and building images corresponding to a target building.

[0049] The initial point cloud data may be point cloud data that has not been subjected to point cloud segmentation processing. In an embodiment of the present application, the initial point cloud data may include building point cloud data corresponding to the target building and other interfering point cloud data that causes interference.

[0050] The building image may be images of the target building in different orientations, including front view images, side view images, and overhead view images.

[0051] Optionally, the server can directly obtain the initial point cloud data corresponding to the target building through a point cloud data acquisition device, which may include a laser radar and a fisheye camera, etc., and the server can directly obtain the building image corresponding to the target building through an image acquisition device; optionally, the server can obtain pre-archived initial point cloud data and building images from a database. For example, the server can filter the data in the database according to the data identifier corresponding to the target building, thereby obtaining the initial point cloud data and building image corresponding to the target building.

[0052] Step 202: Determine the spatial position information of the target frame in the point cloud space corresponding to the initial point cloud data based on the building image.

[0053] The target frame is the location frame corresponding to the target building in the building image.

[0054] In one possible implementation, the server can obtain the planar position information corresponding to the target frame that fits the outline of the target building by identifying and detecting the target building in the building image. Based on the planar position information, the server can project the target frame into the point cloud space, thereby determining the spatial position information of the target frame in the point cloud space.

[0055] Optionally, the server can identify the outline of the target building to obtain a bounding box corresponding to the target building, which is the target box. The server can use the position information of the target box on the building image as the plane position information corresponding to the target box; optionally, the building image includes the path of the target box, for example, the outline of the target building depicted by a red line in the building image is the path of the target box. The server can identify the target box in the building image according to preset conditions, thereby obtaining the position information of the target box on the building image as the plane position information corresponding to the target box.

[0056] Regarding the process of the server determining the spatial position information of the target frame in the point cloud space based on the plane position information, optionally, the server can input the plane position information into a pre-trained position information conversion model to obtain the spatial position information output by the position information conversion model; optionally, the server can obtain the IMU information corresponding to the acquisition device, and determine the conversion relationship between the two-dimensional coordinates corresponding to the building image and the three-dimensional coordinates corresponding to the point cloud space based on the IMU information. Using this conversion relationship, the server can project the target frame into the point cloud space based on the plane position information corresponding to the target frame, thereby obtaining the spatial position information of the target frame in the point cloud space.

[0057] Step 203 : performing point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

[0058] After determining the spatial position information corresponding to the target frame, the server can perform point cloud segmentation on the initial point cloud data according to the spatial position information. Optionally, the server can generate a specific segmentation path based on the spatial position information. The server can perform point cloud segmentation on the initial point cloud data according to the segmentation path, and use the point cloud data within the segmentation path as the building point cloud data corresponding to the target building; optionally, the server can directly cut out the candidate point cloud space according to the spatial position information corresponding to the target frame, and the point cloud data within the candidate point cloud space is the building point cloud data.

[0059] In the above embodiment, the spatial position information of the target frame corresponding to the target building in the point cloud space is determined through the building image, and the initial point cloud data is segmented using the spatial position information, thereby automatically removing the point cloud data causing interference in the initial point cloud data, and obtaining the building point cloud data corresponding to the target building. This avoids the problem of low segmentation efficiency in manual point cloud segmentation in traditional technologies. The technical solution provided in this application can realize automated point cloud segmentation and improve segmentation efficiency.

[0060] In one embodiment, based on the above Figure 2 The embodiment shown, see Figure 3 , this embodiment relates to a process of determining the spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data based on a building image. Figure 3 As shown, step 202 may include step 301 and step 302 .

[0061] Step 301: Determine the plane position information of the target frame in the building image according to the building image.

[0062] In an embodiment of the present application, the plane position information is the position information of the target frame in the building image. For example, a plane coordinate system is established in the building image, and the coordinates of the target frame are the plane position information of the target frame in the building image.

[0063] In a possible implementation, the server may perform target detection processing on the building image to obtain plane position information.

[0064] Regarding target detection processing, optionally, the server can use the outline of the target building as the object of target detection. By identifying the outline of the target building, the server can identify the bounding box corresponding to the target building, which is the target box. The server can use the position information of the target box on the building image as the plane position information corresponding to the target box.

[0065] Optionally, the building image includes the path of the target box. For example, the outline of the target building depicted by the red line in the building image is the path of the target box. The server can use the red line as the object of target detection and identify the target box in the building image based on this, thereby obtaining the position information of the target box on the building image as the plane position information corresponding to the target box.

[0066] Step 302: Determine spatial position information based on the planar position information.

[0067] After obtaining the planar position information corresponding to the target frame, the server can determine the spatial position information of the target frame in the point cloud space.

[0068] In a possible implementation, the server may input the planar position information into a pre-trained position information conversion model, thereby obtaining the spatial position information output by the position information conversion model.

[0069] In another possible implementation, the server can obtain IMU data corresponding to the target building, and based on the IMU data, project the planar position information into the point cloud space corresponding to the initial point cloud data to obtain spatial position information, wherein the IMU data can reflect the motion information of the acquisition device when collecting the building image corresponding to the target building and the initial point cloud data.

[0070] In one embodiment, based on the above Figure 2 The embodiment shown, see Figure 4 This embodiment involves a process of performing point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain the building point cloud data corresponding to the target building. Figure 4 As shown, step 203 may include step 401 and step 402.

[0071] Step 401: Determine a point cloud segmentation path based on spatial position information.

[0072] The point cloud segmentation path may be a cutting space in the point cloud space, and the server may cut the point cloud space through the point cloud segmentation path to obtain cut point cloud data.

[0073] In a possible implementation, the server may perform fitting processing on the spatial position information and the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame, and then determine the point cloud segmentation path based on the spatial position information and the normal vector.

[0074] The point cloud plane may be obtained after performing point cloud preprocessing on the initial point cloud data, and the point cloud preprocessing may include downsampling, normal vector calculation, and Poisson reconstruction.

[0075] Specifically, after obtaining the spatial position information, the server can perform plane fitting on the target box and the point cloud plane based on the spatial position information, and calculate the normal vector of the target box fitted on the point cloud plane to obtain the normal vector of the target box in the point cloud space. Then, the server can determine the point cloud segmentation path based on the spatial position information corresponding to the target box and the direction of the normal vector.

[0076] Step 402 : Segment the initial point cloud data according to the point cloud segmentation path to obtain building point cloud data.

[0077] After obtaining the point cloud segmentation path, the server can segment the initial point cloud data according to the point cloud segmentation path. In an embodiment of the present application, the server can use the point cloud data within the point cloud segmentation path as the building point cloud data corresponding to the target building.

[0078] In one embodiment, referring to Figure 5 , provides an exemplary point cloud segmentation method, which can be applied in the implementation environment shown in Figure 1.

[0079] Step 501: Acquire initial point cloud data and building images corresponding to a target building.

[0080] Step 502: Perform target detection processing on the building image to obtain plane position information.

[0081] Step 503: Acquire IMU data corresponding to the target building.

[0082] Step 504 : Project the plane position information into the point cloud space corresponding to the initial point cloud data according to the IMU data to obtain the spatial position information.

[0083] The target frame is the location frame corresponding to the target building in the building image.

[0084] Step 505 : Fitting the spatial position information with the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame.

[0085] Step 506: Determine the point cloud segmentation path according to the spatial position information and the normal vector.

[0086] Step 507 : Segment the initial point cloud data according to the point cloud segmentation path to obtain building point cloud data.

[0087] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0088] Based on the same inventive concept, embodiments of the present application also provide a house point cloud segmentation device for implementing the aforementioned house point cloud segmentation method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more house point cloud segmentation device embodiments provided below can be found in the limitations of the house point cloud segmentation method described above and will not be repeated here.

[0089] In an exemplary embodiment, Figure 6 As shown, a house point cloud segmentation device is provided, comprising: an acquisition module 601, a target frame position determination module 602 and a segmentation module 603, wherein:

[0090] An acquisition module 601 is used to acquire initial point cloud data and building images corresponding to a target building;

[0091] A target frame position determination module 602 is configured to determine, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, wherein the target frame is a position frame corresponding to the target building in the building image;

[0092] The segmentation module 603 is configured to perform point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

[0093] In one embodiment, the target frame position determination module 602 includes:

[0094] a plane position determining unit, configured to determine plane position information of the target frame in the building image based on the building image;

[0095] A spatial position determining unit is configured to determine the spatial position information according to the planar position information.

[0096] In one embodiment, the spatial position determination unit is specifically configured to perform:

[0097] Obtaining IMU data corresponding to the target building;

[0098] According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

[0099] In one embodiment, the plane position determination unit is specifically configured to perform:

[0100] Perform target detection processing on the building image to obtain the plane position information.

[0101] In one embodiment, the segmentation module 603 includes:

[0102] a path determination unit, configured to determine a point cloud segmentation path according to the spatial position information;

[0103] A segmentation processing unit is used to perform segmentation processing on the initial point cloud data according to the point cloud segmentation path to obtain the building point cloud data.

[0104] In one embodiment, the path determination unit is specifically configured to perform:

[0105] Fitting the spatial position information to the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame;

[0106] The point cloud segmentation path is determined according to the spatial position information and the normal vector.

[0107] Each module in the aforementioned building point cloud segmentation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0108] In an exemplary embodiment, a computer device is provided. The computer device may be a server included in a house point cloud segmentation device. The internal structure diagram thereof may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store house point cloud segmentation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a house point cloud segmentation method is implemented.

[0109] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0110] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0111] Obtain the initial point cloud data and building image corresponding to the target building;

[0112] Determining, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, the target frame being a position frame corresponding to the target building in the building image;

[0113] Point cloud segmentation processing is performed on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

[0114] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0115] Determining, based on the building image, planar position information of the target frame in the building image;

[0116] The spatial position information is determined according to the planar position information.

[0117] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0118] Obtaining IMU data corresponding to the target building;

[0119] According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

[0120] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0121] Perform target detection processing on the building image to obtain the plane position information.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] Determining a point cloud segmentation path according to the spatial position information;

[0124] The initial point cloud data is segmented according to the point cloud segmentation path to obtain the building point cloud data.

[0125] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0126] Fitting the spatial position information to the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame;

[0127] The point cloud segmentation path is determined according to the spatial position information and the normal vector.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0129] Obtain the initial point cloud data and building image corresponding to the target building;

[0130] Determining, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, the target frame being a position frame corresponding to the target building in the building image;

[0131] Point cloud segmentation processing is performed on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

[0132] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0133] Determining, based on the building image, planar position information of the target frame in the building image;

[0134] The spatial position information is determined according to the planar position information.

[0135] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0136] Obtaining IMU data corresponding to the target building;

[0137] According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

[0138] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0139] Perform target detection processing on the building image to obtain the plane position information.

[0140] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0141] Determining a point cloud segmentation path according to the spatial position information;

[0142] The initial point cloud data is segmented according to the point cloud segmentation path to obtain the building point cloud data.

[0143] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0144] Fitting the spatial position information to the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame;

[0145] The point cloud segmentation path is determined according to the spatial position information and the normal vector.

[0146] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0147] Obtain the initial point cloud data and building image corresponding to the target building;

[0148] Determining, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, the target frame being a position frame corresponding to the target building in the building image;

[0149] Point cloud segmentation processing is performed on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0151] Determining, based on the building image, planar position information of the target frame in the building image;

[0152] The spatial position information is determined according to the planar position information.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0154] Obtaining IMU data corresponding to the target building;

[0155] According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0157] Perform target detection processing on the building image to obtain the plane position information.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0159] Determining a point cloud segmentation path according to the spatial position information;

[0160] The initial point cloud data is segmented according to the point cloud segmentation path to obtain the building point cloud data.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0162] Fitting the spatial position information to the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame;

[0163] The point cloud segmentation path is determined according to the spatial position information and the normal vector.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0166] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A house point cloud segmentation method, characterized in that: The method comprises: Obtain the initial point cloud data and building image corresponding to the target building; Determining, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, the target frame being a position frame corresponding to the target building in the building image; Point cloud segmentation processing is performed on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

2. The method according to claim 1, characterized in that Determining, based on the building image, spatial position information of the target frame in the point cloud space corresponding to the initial point cloud data includes: Determining, based on the building image, planar position information of the target frame in the building image; The spatial position information is determined according to the planar position information.

3. The method according to claim 2, characterized in that The determining the spatial position information according to the planar position information includes: Obtaining IMU data corresponding to the target building; According to the IMU data, the plane position information is projected into the point cloud space corresponding to the initial point cloud data to obtain the spatial position information.

4. The method according to claim 2, characterized in that The determining, based on the building image, the planar position information of the target frame in the building image includes: Perform target detection processing on the building image to obtain the plane position information.

5. The method according to claim 1, wherein The performing point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building includes: Determining a point cloud segmentation path according to the spatial position information; The initial point cloud data is segmented according to the point cloud segmentation path to obtain the building point cloud data.

6. The method according to claim 5, characterized in that The determining of the point cloud segmentation path according to the spatial position information includes: Fitting the spatial position information to the point cloud plane corresponding to the initial point cloud data to obtain a normal vector corresponding to the target frame; The point cloud segmentation path is determined according to the spatial position information and the normal vector.

7. A house point cloud segmentation device, characterized in that: The device comprises: An acquisition module is used to obtain the initial point cloud data and building images corresponding to the target building; a target frame position determination module, configured to determine, based on the building image, spatial position information of a target frame in the point cloud space corresponding to the initial point cloud data, wherein the target frame is a position frame corresponding to the target building in the building image; The segmentation module is used to perform point cloud segmentation processing on the initial point cloud data according to the spatial position information to obtain building point cloud data corresponding to the target building.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images