Point cloud data processing method, device, equipment and storage medium

By classifying and screening indoor point cloud data, using closed space and distance mean, the problem of low manual screening efficiency is solved, and efficient and accurate point cloud data processing is achieved.

CN114359370BActive Publication Date: 2024-11-05CHINA UNITED NETWORK COMM GRP CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111674133.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-31
Publication Date
2024-11-05
Estimated Expiration
2041-12-31

AI Technical Summary

Technical Problem

The method of manually screening point cloud data has errors and is inefficient, making it difficult to efficiently process multiple point cloud data in the room.

Method used

By classifying indoor point cloud data, the enclosed space composed of adjacent planes is determined, point cloud data that does not belong to the space is deleted, and three-dimensional coordinates and distance mean are used for filtering, improving the screening efficiency of point cloud data.

Benefits of technology

It realizes rapid and accurate screening of indoor point cloud data, improves the processing efficiency of point cloud data, and reduces manual errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114359370B_ABST
    Figure CN114359370B_ABST
Patent Text Reader

Abstract

The present application provides a method, device, equipment and storage medium for processing point cloud data, which relates to the field of data processing, can solve the technical problem of low screening efficiency of point cloud data, and can improve the screening efficiency of indoor point cloud data. The method includes: obtaining multiple point cloud data in the room, the multiple point cloud data are used to characterize the structural characteristics of the room, the room includes multiple planes, and the adjacent planes in the multiple planes are perpendicular to each other; classifying the multiple point cloud data to obtain multiple point cloud data sets, and the point cloud data set corresponds to a plane; according to the multiple point cloud data sets, determining the first closed space, the first closed space is the largest closed space composed of multiple planes; deleting the point cloud data that does not belong to the first closed space in the multiple point cloud data, and obtaining multiple point cloud data inside the room.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] During the construction of a house, the data mapping of the indoor floor and wall of the house is becoming increasingly complicated. Usually, data mapping of the house is carried out by manual measurement. However, manual measurement is not only time-consuming and labor-intensive, but also prone to errors in data mapping results.

[0003] In the prior art, a laser scanning device can be used to scan indoor walls to obtain multiple point cloud data of the room. Then, the multiple point cloud data of the room are manually screened to remove the point cloud data that does not belong to the indoor range. However, since the method of manually screening point cloud data not only has large errors, but also has low efficiency when there are a lot of point cloud data indoors. Therefore, how to improve the screening efficiency of indoor point cloud data has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a point cloud data processing method, device, equipment and storage medium to improve the screening efficiency of indoor point cloud data.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for processing point cloud data, characterized in that the method includes: acquiring multiple point cloud data indoors, the multiple point cloud data are used to characterize the structural characteristics of the indoors, the indoors including multiple planes, and adjacent planes in the multiple planes are perpendicular to each other; classifying the multiple point cloud data to obtain multiple point cloud data sets, the point cloud data sets corresponding to one plane; determining a first closed space based on the multiple point cloud data sets, the first closed space being the largest closed space formed by multiple planes; deleting the point cloud data in the multiple point cloud data that does not belong to the first closed space, to obtain multiple point cloud data inside the indoors.

[0007] Optionally, multiple point cloud data are classified to determine multiple point cloud data sets, including: determining multiple point cloud data sets based on three-dimensional coordinates of the multiple point cloud data, and all point cloud data in the point cloud data sets have the same value in the same dimension or two dimensions.

[0008] Optionally, the edges of one or more point cloud data in the point cloud data set are expanded along a first direction to obtain multiple first planes, where the first direction is the expansion direction of the planes corresponding to the point cloud data set; the intersection lines of two intersecting planes in the multiple first planes are interrupted to obtain multiple closed planes.

[0009] Optionally, before classifying multiple point cloud data, the method also includes: determining a first value of each point cloud data in the multiple point cloud data, the first value of the point cloud data being the average of the distances between the point cloud data and multiple adjacent point cloud data; for any point cloud data, if the ratio of the distance between the point cloud data and multiple adjacent point cloud data to the average of the first values ​​of the multiple point cloud data is greater than a preset value, the point cloud data is deleted.

[0010] Optionally, determining the first closed space based on multiple point cloud data sets includes: determining the spatial volume of one or more closed spaces formed by multiple closed planes; and taking the closed space with the largest spatial volume among the multiple closed spaces as the first closed space.

[0011] In a second aspect, the present application provides a point cloud data processing device, characterized in that it includes: an acquisition unit, a classification unit, a deletion unit and a determination unit; the acquisition unit is used to acquire multiple point cloud data in the room, the multiple point cloud data are used to characterize the structural characteristics of the room, the room includes multiple planes, and adjacent planes in the multiple planes are perpendicular to each other; the classification unit is used to classify the multiple point cloud data to obtain multiple point cloud data sets, and the point cloud data set corresponds to one plane; the determination unit is used to determine a first closed space based on the multiple point cloud data sets, and the first closed space is the largest closed space composed of multiple planes; the deletion unit is used to delete the point cloud data that does not belong to the first closed space in the multiple point cloud data to obtain multiple point cloud data inside the room.

[0012] Optionally, the determination unit is specifically used to: determine multiple point cloud data sets according to the three-dimensional coordinates of the multiple point cloud data, and all point cloud data in the point cloud data sets have the same value in the same dimension or two dimensions.

[0013] Optionally, the processing unit is used to expand the edges of one or more point cloud data in the point cloud data set along a first direction to obtain multiple first planes, where the first direction is the expansion direction of the plane corresponding to the point cloud data set; the processing unit is also used to interrupt the intersection line of two intersecting planes in the multiple first planes to obtain multiple closed planes.

[0014] Optionally, the determination unit is also used to determine a first value of each point cloud data in a plurality of point cloud data, the first value of the point cloud data being the average of the distances between the point cloud data and a plurality of adjacent point cloud data; for any point cloud data, if the ratio of the distance between the point cloud data and a plurality of adjacent point cloud data to the average of the first values ​​of the plurality of point cloud data is greater than a preset value, the point cloud data is deleted.

[0015] Optionally, a determination unit is specifically used to determine the spatial volume of one or more closed spaces formed by multiple closed planes;

[0016] The closed space with the largest spatial volume among the multiple closed spaces is taken as the first closed space.

[0017] In a third aspect, the present application provides a point cloud data processing device, the point cloud data processing device comprising: a processor, a data processing interface and a memory. The memory is used to store one or more programs. The one or more programs include computer executable instructions. When the point cloud data processing device is running, the processor executes the computer executable instructions stored in the memory, so that the point cloud data processing device performs the point cloud data processing method of any one of the first aspect and its various optional implementations.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored. When a computer executes the instructions, the computer executes the method for processing point cloud data of any one of the above-mentioned first aspect and its various optional implementation methods.

[0019] The present application provides a method for processing point cloud data. After acquiring multiple point cloud data indoors, the present application first classifies the multiple point cloud data to determine multiple point cloud data sets, each of which can represent a plane. That is, multiple planes can be obtained by classifying the point cloud data. Then, due to the perpendicular relationship between adjacent planes in the multiple planes, the multiple planes can constitute one or more closed spaces. Since the closed space with the largest spatial volume in the one or more closed spaces is the real space indoors, the point cloud data that does not belong to the closed space with the largest spatial volume in the above-mentioned multiple point cloud data can be deleted, and the point cloud data belonging to the indoors can be obtained. Compared with the method of manually screening point cloud data, in the present application, by classifying the point cloud data and judging whether it belongs to the corresponding point cloud data indoors, the multiple point cloud data obtained can be quickly screened, thereby improving the screening efficiency of the point cloud data. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the structure of a point cloud data processing system 10 provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the structure of a point cloud data processing device provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of a process of processing point cloud data provided in an embodiment of the present application;

[0023] Figure 4a A schematic diagram of indoor point cloud data provided by an embodiment of the present application;

[0024] Figure 4b A schematic diagram of point cloud data of an indoor space provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of a process of processing point cloud data provided in an embodiment of the present application;

[0026] Figure 6a A schematic diagram of point cloud data expansion provided in an embodiment of the present application;

[0027] Figure 6b A schematic diagram of the intersection of point cloud data and corresponding planes provided in an embodiment of the present application;

[0028] Figure 7 A schematic diagram of a closed plane for processing point cloud data provided in an embodiment of the present application;

[0029] Figure 8 A flowchart of another method for processing point cloud data provided in an embodiment of the present application;

[0030] Fig. 9 A flowchart of another method for processing point cloud data provided in an embodiment of the present application;

[0031] Fig.10 A schematic diagram of the structure of a point cloud data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following is a detailed description of a point cloud data processing method, device, equipment and storage medium provided in an embodiment of the present application in conjunction with the accompanying drawings.

[0033] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0034] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0035] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0036] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0037] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0038] Before introducing the embodiments of the present application, some terms involved in the embodiments of the present application are explained:

[0039] Point cloud data: refers to a set of vectors in a three-dimensional coordinate system. Point cloud data can be recorded in the form of three-dimensional coordinates. For example, the three-dimensional coordinates of a point cloud data can be (X0, Y0, Z0).

[0040] In some examples, the point cloud data may also include color information and reflection intensity information. The color information may be an indoor color image acquired by a camera, and the color information may be assigned to the point cloud data of the corresponding point. The reflection intensity information may be used to analyze the surface material, roughness, and incident angle direction of the indoor wall. The incident angle direction is the angle between the incident laser and the normal direction of the wall when the data acquisition device acquires the point cloud data of the indoor wall.

[0041] A method for processing point cloud data provided by an embodiment of the present application is described below in conjunction with the accompanying drawings.

[0042] The data processing method provided in the embodiment of the present application can be applied to Figure 1 In the point cloud data processing system shown in FIG. Figure 1 As shown, the point cloud data processing system 10 may include a point cloud data processing device 11 and a point cloud data acquisition device 12. The point cloud data processing device 11 and the point cloud data acquisition device 12 may be connected by wireless communication or by wired communication.

[0043] The point cloud data acquisition device 12 is used to acquire point cloud data and feed the point cloud data back to the point cloud data processing device 11 .

[0044] The point cloud data processing device 11 is used to process the point cloud data. For example, a three-dimensional image composed of the point cloud data can be displayed in a visual manner.

[0045] In practical applications, the point cloud data processing device 11 can be a computer or other similar devices with data processing capabilities. The point cloud data acquisition device 12 can be a laser scanning device or other similar devices with scanning capabilities, which is not limited in this application.

[0046] It should be noted that Figure 1 This is only an exemplary architecture diagram. Figure 1 In addition to the functional units shown in , the data processing system may also include other functional units, which is not limited in the embodiments of the present application.

[0047] In the specific implementation, Figure 1 Each device in the Figure 2 The structure shown, or including Figure 2 Parts shown. Figure 2 A schematic diagram of the composition of a point cloud data processing device 20 provided in an embodiment of the present application, wherein the point cloud data processing device 20 includes a processor 201 , a data processing interface 202 , a data processing circuit 203 and a memory 204 .

[0048] The processor 201 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 may also be other devices with processing functions, such as circuits, devices, or software modules, without limitation. In one example, the processor 201 may include one or more CPUs, for example, Figure 2 CPU0 and CPU1 in.

[0049] The data processing interface 202 is used to process data with other devices or other data processing networks. The other data processing networks may be Ethernet, radio access networks (RAN equipment), wireless local area networks (WLAN), etc. The data processing interface may be a module, a circuit, a data processing interface or any device capable of implementing data processing.

[0050] The data processing circuit 203 is used to transmit messages between various components included in the point cloud data processing system.

[0051] The memory 204 is used to store instructions, where the instructions may be computer programs.

[0052] Among them, the memory 204 can be a read-only memory (ROM) or other types of static storage devices that can store static messages and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store messages and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0053] It should be noted that the memory 204 can exist independently of the processor 201, or can be integrated with the processor 201. The memory 204 can be used to store instructions or program codes or some network data, etc. The memory 302 can be located in the point cloud data processing device 20, or can be located outside the point cloud data processing device 20, without limitation. The processor 201 is used to execute the instructions stored in the memory 204 to implement the point cloud data processing method provided in the following embodiments of the present application.

[0054] As an optional implementation, the point cloud data processing device 20 includes multiple processors, for example, Figure 2 In addition to the processor 201, a processor 207 may also be included.

[0055] As an optional implementation, the point cloud data processing device 20 further includes an output device 205 and an input device 206. Exemplarily, the input device 206 is a device such as a keyboard, a mouse, a microphone or a joystick, and the output device 205 is a device such as a display screen and a speaker.

[0056] In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices.

[0057] In addition, the actions, terms, etc. involved in the various embodiments of the present application can refer to each other without limitation. The message name or parameter name in the message exchanged between the various devices in the embodiments of the present application is only an example, and other names can also be used in the specific implementation without limitation.

[0058] An embodiment of the present application provides a method for processing point cloud data, which can be applied to the above-mentioned point cloud data processing device, and can also be applied to a processing device similar to the point cloud data processing device.

[0059] The present application embodiment is described by taking the point cloud data processing method adapted to the above-mentioned point cloud data processing device as an example. Figure 3 As shown, the method may include S301-S304:

[0060] S301. A point cloud data processing device obtains a plurality of point cloud data indoors.

[0061] Among them, the point cloud data processing equipment can be Figure 1 The point cloud data processing device 11 may also be a device in the point cloud data processing device 11, such as a chip.

[0062] Among them, multiple point cloud data are used to characterize the structural features of the room. The room includes multiple planes, and adjacent planes in the multiple planes are perpendicular to each other.

[0063] The multiple planes in the room may include a wall, a floor and a top plane in the room. The wall may be perpendicular to the floor and the top plane.

[0064] As a possible implementation, the point cloud data acquisition device can collect multiple point cloud data in the room and send the multiple point cloud data in the room to the point cloud data processing device. Correspondingly, the point cloud data processing device receives the multiple point cloud data in the room from the point cloud data acquisition device.

[0065] Among them, the point cloud data acquisition equipment can be Figure 1 The point cloud data acquisition device 12 may also be a device in the point cloud data acquisition device 12, such as a chip.

[0066] For example, the point cloud data acquisition device can be set in the middle of the room. In response to the acquisition operation, the point cloud data acquisition device can automatically start the point cloud data measurement function to collect the point cloud data in the room. After the point cloud data acquisition device measures the point cloud data in the room, the collected point cloud data can be sent to the point cloud data processing device.

[0067] For another example, a surveyor may also use a point cloud data acquisition device to manually measure indoor point cloud data. The point cloud data acquisition device may respond to the surveyor's upload operation and send the collected point cloud data to the point cloud data processing device.

[0068] It should be noted that the point cloud data collected by the point cloud data collection device may include point cloud data of multiple planes in the room, and may also include point cloud data of other areas. For example, when the door or window in the room is open, the laser emitted by the point cloud data collection device can be projected onto the wall of other areas through the door or window. At this time, the point cloud data of the door or window area collected by the point cloud data collection device is the point cloud data of other walls.

[0069] For example, Figure 4a As shown in the figure, since the indoor door or window is open, the point cloud data acquisition device will scan point cloud data that does not belong to the indoor area. Figure 4a The point cloud data of area a, area b, and area c in the figure are point cloud data that do not belong to the interior of the room.

[0070] S302: The point cloud data processing device classifies the multiple point cloud data to obtain multiple point cloud data sets.

[0071] Among them, one point cloud data set corresponds to one plane, and each point cloud data set includes multiple point cloud data of one plane.

[0072] As a possible implementation method, a point cloud data processing device can determine the correspondence between point cloud data and planes based on the characteristic that adjacent planes in multiple planes are perpendicular to each other, and regard multiple point cloud data belonging to the same plane as a point cloud set.

[0073] For example, for a plane formed by the X-axis and the Y-axis, the value of the Z-axis direction in the point cloud data in the plane is the same. For a plane formed by the X-axis and the Z-axis, the value of the Y-axis direction in the point cloud data in the plane is the same. For a plane formed by the Y-axis and the Z-axis, the value of the X-axis direction in the point cloud data in the plane is the same.

[0074] S303: The point cloud data processing device determines a first closed space according to multiple point cloud data sets.

[0075] Among them, the first closed space is the largest closed space formed by multiple planes.

[0076] As a possible implementation method, the point cloud data processing device can expand the edges of one or more point cloud data in each point cloud data set along a first direction, where the first direction is the expansion direction of the plane corresponding to the point cloud data set. Then, the intersection lines of two intersecting planes in the multiple planes are interrupted to obtain multiple closed planes. The multiple closed planes can form one or more closed spaces, and the largest closed space in the one or more closed spaces is taken as the first closed space. For details, please refer to the subsequent description, which will not be repeated here.

[0077] For example, Figure 4a The point cloud data shown can form one or more closed spaces, and the largest closed space in the one or more closed spaces can be Figure 4b express.

[0078] S304: The point cloud data processing device deletes the point cloud data that does not belong to the first closed space from the multiple point cloud data to obtain multiple point cloud data inside the room.

[0079] The point cloud data that does not belong to the first closed space may be point cloud data that does not belong to the interior of the room scanned by the point cloud data acquisition device due to the doors and windows being open. Figure 4a shown.

[0080] In one example, the point cloud data processing device deletes the point cloud data that does not belong to the first closed space from the multiple point cloud data, and after obtaining the multiple point cloud data inside the room, the schematic diagram of the multiple point cloud data inside the room can be as follows: Figure 4b shown.

[0081] After acquiring multiple point cloud data indoors, the present application first classifies the multiple point cloud data to determine multiple point cloud data sets, each of which can represent a plane. That is, multiple planes can be obtained by classifying the point cloud data. Then, due to the perpendicular relationship between adjacent planes in the multiple planes, the multiple planes can constitute one or more closed spaces. Since the closed space with the largest spatial volume in the one or more closed spaces is the real indoor space, the point cloud data that does not belong to the closed space with the largest spatial volume in the above multiple point cloud data can be deleted to obtain the point cloud data belonging to the indoor space. Compared with the manual screening of point cloud data, in the present application, by classifying the point cloud data and judging whether it belongs to the corresponding point cloud data indoors, the multiple point cloud data obtained can be quickly screened, thereby improving the screening efficiency of the point cloud data.

[0082] In a possible embodiment, in order to determine multiple point cloud data sets, the processing S302 of the point cloud data specifically includes the following: the point cloud data processing device determines multiple point cloud data sets according to the three-dimensional coordinates of the multiple point cloud data.

[0083] Among them, all point cloud data in the point cloud data set have the same value in the same dimension or two dimensions.

[0084] In a possible implementation, a point cloud data processing device may treat point cloud data with the same values ​​in the same dimension or two dimensions as a point cloud data set, and process all point cloud data in this manner to obtain multiple point cloud data sets.

[0085] Exemplarily, the point cloud data processing device can use the point cloud data acquisition device as the origin, the direction parallel to the indoor ground as the Z axis, the vertical direction of the surface with the largest number of point cloud data as the X axis, and finally the direction perpendicular to both the Z axis and the X axis as the Y axis, thereby establishing a three-dimensional coordinate system. The three-dimensional coordinates of the point cloud data in the plane formed by the X axis and the Y axis can all be represented by (a, b, 0); wherein a and b are any values, and the values ​​of a and b can be equal or unequal. Multiple point cloud data with the same values ​​in the same dimension or two dimensions can determine a point cloud data set, and thus, point cloud data on multiple planes can form multiple point cloud data sets.

[0086] Therefore, the present application can quickly determine a set of point cloud data belonging to the same plane by analyzing the three-dimensional coordinates of each point cloud data.

[0087] In a possible embodiment, Figure 5 As shown, the method for processing point cloud data provided in the embodiment of the present application may also include the following S401-S402:

[0088] S401. A point cloud data processing device expands edges of one or more point cloud data in a point cloud data set along a first direction to obtain a plurality of first planes.

[0089] The first direction is the expansion direction of the plane corresponding to the point cloud data set.

[0090] In a possible implementation, the point cloud data processing device can expand one or more point cloud data in the plane direction corresponding to the point cloud data set according to the preset internal visualization software to obtain multiple first planes. The expansion means extending the points represented by the point cloud data.

[0091] For example, Figure 6a As shown, the point cloud data can be unfolded in the direction of the plane in which it is located.

[0092] It should be noted that when two first planes intersect, the point cloud data processing device may stop expanding the first planes at the intersection line.

[0093] For example, Figure 6b As shown, there is a first intersection line between plane a and plane b during the unfolding process, and plane a and plane b stop unfolding at the first intersection line.

[0094] S402: The point cloud data processing device interrupts the intersection line of two intersecting planes among the multiple first planes to obtain multiple closed planes.

[0095] Wherein, interrupting the intersection line of two intersecting planes among the plurality of first planes may refer to processing the point cloud data to segment the intersection line of two intersecting planes among the plurality of first planes, and stopping the first plane from unfolding at the intersection line, thereby obtaining a plurality of closed planes or a set of point clouds constituting the closed planes.

[0096] For example, Figure 7 As shown, the c side, the d side, the e side and the f side are sides of the closed plane 4022. Each side is an intersection line between the first plane 4021 and an adjacent and perpendicular plane.

[0097] Therefore, the present application can quickly obtain a closed plane formed by point cloud data.

[0098] In a possible embodiment, before classifying a plurality of point cloud data, Figure 8 As shown, the point cloud data processing method provided in the embodiment of the present application may also include the following S501-S502.

[0099] S501. A point cloud data processing device determines a first value of each point cloud data in a plurality of point cloud data.

[0100] The first value of the point cloud data is the average value of the distance between the point cloud data and a plurality of adjacent point cloud data.

[0101] It should be noted that the number of any point cloud data and the adjacent multiple point cloud data can be preset. For example, the number of the adjacent multiple point cloud data can be 5.

[0102] For example, taking the example that the distances between point cloud data a and five adjacent point cloud data are 1 cm, 1.5 cm, 1.5 cm, 2 cm, and 2 cm respectively, the first value of point cloud data a is 1.6 cm.

[0103] S502: For any point cloud data, if the ratio of the distance between the point cloud data and a plurality of adjacent point cloud data to the average of the first values ​​of the plurality of point cloud data is greater than a preset value, the point cloud data processing device deletes the point cloud data.

[0104] The first values ​​of the plurality of point cloud data may be the first values ​​of all point cloud data. The size of the preset value may be set as required, for example, may be 10, without limitation.

[0105] Therefore, the present application calculates the average of the first value of each point cloud data and the first values ​​of other multiple point cloud data. When the ratio between the first value of the point cloud data and the average of the first values ​​of other multiple point cloud data is less than a preset value, the point cloud data can be deleted, thereby improving the accuracy of the acquired point cloud data.

[0106] In a possible embodiment, Fig. 9 As shown, in order to determine the first closed space, the processing S303 of the above point cloud data specifically includes the following S3031-S3032.

[0107] S3031. The point cloud data processing device determines the spatial volume of one or more closed spaces formed by multiple closed planes.

[0108] As a possible implementation, for the spatial volume of the one or more closed spaces, the point cloud data processing device can calculate the lengths of multiple sidelines of the closed space, and calculate the volume of the closed space based on the lengths of the multiple sidelines. The specific calculation method can refer to the prior art and will not be described in detail.

[0109] S3032. The point cloud data processing device takes the closed space with the largest spatial volume among the multiple closed spaces as the first closed space.

[0110] Therefore, in the present application, by taking the enclosed space with the largest spatial volume as the first enclosed space, the enclosed plane belonging to the room can be accurately determined.

[0111] In some embodiments, the point cloud data processing device may further perform topological correction on the obtained multiple point cloud data inside the room.

[0112] The topology correction may supplement the point cloud data that has been removed by mistake from certain planes, and / or the missing point cloud data at the intersection of adjacent first planes.

[0113] For example, the top of a room is a solid surface, but after the above point cloud data processing, the plane formed by the point cloud data of the top of the room has gaps. At this time, the point cloud data processing device can perform topological correction on the point cloud data of the top, so as to obtain a complete point cloud set of the roof.

[0114] In some embodiments, the point cloud data processing device can compare the first enclosed space obtained by processing the above point cloud data with the three-dimensional image of the room. If abnormal point cloud data appears between the first enclosed space and the three-dimensional image of the room, such as point cloud data still exists at the window position of the first enclosed space, the point cloud data processing device can delete the point cloud data.

[0115] The embodiment of the present application can divide the server into functional modules or functional units according to the above method example. For example, each functional module or functional unit can be divided according to each function, or two or more functions can be integrated into two modules. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules or functional units. Among them, the division of modules or units in the embodiment of the present application is schematic, which is only a logical function division. There may be other division methods in actual implementation.

[0116] Fig.10 FIG. 2 shows a possible structural diagram of a point cloud data processing device involved in the above embodiment. Fig.10 As shown, the point cloud data processing device 60 includes an acquisition unit 601 , a classification unit 602 , a determination unit 603 , a deletion unit 604 , and a processing unit 605 .

[0117] The acquisition unit 601 is used to acquire multiple point cloud data in the room, and the multiple point cloud data are used to characterize the structural features of the room. The room includes multiple planes, and the adjacent planes in the multiple planes are perpendicular to each other. Figure 3 As shown, the acquisition unit 601 can be used to execute S301.

[0118] The classification unit 602 is used to classify the multiple point cloud data to obtain multiple point cloud data sets, where the point cloud data sets correspond to a plane. Figure 3 As shown, the classification unit 602 can be used to execute S302.

[0119] The determination unit 603 is used to determine a first closed space according to the plurality of point cloud data sets, where the first closed space is the largest closed space formed by the plurality of planes. Figure 3 As shown, the determining unit 603 can be used to execute S302.

[0120] The deleting unit 604 is used to delete the point cloud data that does not belong to the first closed space from the multiple point cloud data to obtain multiple point cloud data inside the room. Figure 3 As shown, the deleting unit 604 can be used to execute S304.

[0121] In one possible design, Fig.10 As shown, the determination unit 603 provided in the embodiment of the present application is specifically used to: determine multiple point cloud data sets based on the three-dimensional coordinates of multiple point cloud data, and all point cloud data in the point cloud data sets have the same numerical value in the same dimension or two dimensions.

[0122] In a possible design, the point cloud data processing device provided in the embodiment of the present application further includes a processing unit 605, the processing unit 605 is used to expand the edge of one or more point cloud data in the point cloud data set along a first direction to obtain multiple first planes, the first direction being the expansion direction of the plane corresponding to the point cloud data set; the processing unit 605 is also used to interrupt the intersection line of two intersecting planes in the multiple first planes to obtain multiple closed planes. For example, Figure 5 As shown, the processing unit 605 can be used to execute S401 - S402 .

[0123] In a possible design, the determination unit 603 provided in the embodiment of the present application is further used to determine a first value of each point cloud data in the plurality of point cloud data, where the first value of the point cloud data is the average value of the distance between the point cloud data and the plurality of adjacent point cloud data. Figure 8 As shown, the determining unit 603 can be used to execute S501.

[0124] The deleting unit 604 is further configured to delete the point cloud data when the ratio between the distance between the point cloud data and the adjacent plurality of point cloud data and the average of the first values ​​of the plurality of point cloud data is greater than a preset value. Figure 8 As shown, the deleting unit 604 can be used to execute S502.

[0125] In a possible design, the determination unit 603 is specifically used to determine the spatial volume of one or more closed spaces formed by multiple closed planes; and to take the closed space with the largest spatial volume among the multiple closed spaces as the first closed space. Fig. 9 As shown, the determination unit 603 can be used to execute S3032.

[0126] The present application provides a method for processing point cloud data. After acquiring multiple point cloud data indoors, the present application first classifies the multiple point cloud data to determine multiple point cloud data sets, each of which can represent a plane. That is, multiple planes can be obtained by classifying the point cloud data. Then, due to the perpendicular relationship between adjacent planes in the multiple planes, the multiple planes can constitute one or more closed spaces. Since the closed space with the largest spatial volume in the one or more closed spaces is the real space indoors, the point cloud data that does not belong to the closed space with the largest spatial volume in the above-mentioned multiple point cloud data can be deleted, and the point cloud data belonging to the indoors can be obtained. Compared with the method of manually screening point cloud data, in the present application, by classifying the point cloud data and judging whether it belongs to the corresponding point cloud data indoors, the multiple point cloud data obtained can be quickly screened, thereby improving the screening efficiency of the point cloud data.

[0127] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0128] An embodiment of the present application provides a computer program product including instructions. When the computer program product is run on a computer, the computer is enabled to execute the method for processing point cloud data of the above method embodiment.

[0129] An embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When a point cloud data processing device executes the instructions, the point cloud data processing device executes each step performed by the point cloud data processing device in the method flow shown in the above method embodiment.

[0130] Among them, the computer readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing point cloud data, characterized in that: include: Acquire a plurality of point cloud data in a room, wherein the plurality of point cloud data are used to characterize structural features of the room, wherein the room includes a plurality of planes, and adjacent planes in the plurality of planes are perpendicular to each other; Determine the plurality of point cloud data sets according to the three-dimensional coordinates of the plurality of point cloud data, wherein all point cloud data in the point cloud data sets have the same value in the same dimension or in two dimensions, and the point cloud data sets correspond to a plane; Expanding edges of one or more point cloud data in the point cloud data set along a first direction to obtain a plurality of first planes, wherein the first direction is an expansion direction of the plane corresponding to the point cloud data set; Interrupting the intersection lines of two intersecting planes among the plurality of first planes to obtain a plurality of closed planes; Determine a first closed space according to the plurality of point cloud data sets, where the first closed space is a maximum closed space formed by the plurality of closed planes; Point cloud data that does not belong to the first closed space in the plurality of point cloud data are deleted to obtain a plurality of point cloud data inside the room.

2. The method according to claim 1, characterized in that: Before classifying the plurality of point cloud data, the method further includes: Determine a first value of each point cloud data in the plurality of point cloud data, wherein the first value of the point cloud data is an average value of distances between the point cloud data and a plurality of adjacent point cloud data; For any point cloud data, if the ratio between the distance between the point cloud data and a plurality of adjacent point cloud data and the average of the first values ​​of the plurality of point cloud data is greater than a preset value, the point cloud data is deleted.

3. The method according to claim 1, characterized in that: The step of determining a first closed space according to the plurality of point cloud data sets comprises: Determining the spatial volume of one or more closed spaces formed by the plurality of closed planes; The closed space with the largest spatial volume among the multiple closed spaces is taken as the first closed space.

4. A point cloud data processing device, characterized in that: include: Acquisition unit, classification unit, deletion unit, processing unit and determination unit; The acquisition unit is used to acquire a plurality of point cloud data in a room, wherein the plurality of point cloud data are used to characterize structural features of the room, wherein the room includes a plurality of planes, and adjacent planes in the plurality of planes are perpendicular to each other; The classification unit is used to classify the plurality of point cloud data to obtain a plurality of point cloud data sets, wherein the point cloud data sets correspond to a plane; The determining unit is used to determine the plurality of point cloud data sets according to the three-dimensional coordinates of the plurality of point cloud data, wherein all point cloud data in the point cloud data sets have the same value in the same dimension or in two dimensions; The processing unit is used to expand the edges of one or more point cloud data in the point cloud data set along a first direction to obtain a plurality of first planes, where the first direction is the expansion direction of the plane corresponding to the point cloud data set; The processing unit is further used to interrupt the intersection line of two intersecting planes among the multiple first planes to obtain multiple closed planes; The determination unit is further used to determine a first closed space based on the multiple point cloud data sets, where the first closed space is the largest closed space formed by the multiple closed planes; the deletion unit is used to delete the point cloud data that does not belong to the first closed space from the multiple point cloud data to obtain multiple point cloud data inside the room.

5. The device according to claim 4, characterized in that The determining unit is further configured to determine a first value of each point cloud data in the plurality of point cloud data, wherein the first value of the point cloud data is an average value of distances between the point cloud data and a plurality of adjacent point cloud data; The deleting unit is further configured to delete the point cloud data when a ratio between a distance between the point cloud data and a plurality of adjacent point cloud data and an average of first values ​​of the plurality of point cloud data is greater than a preset value.

6. The device according to claim 4, characterized in that The determining unit is specifically used to determine the spatial volume of one or more closed spaces formed by the multiple closed planes; The closed space with the largest spatial volume among the multiple closed spaces is taken as the first closed space.

7. A point cloud data processing device, characterized in that: The point cloud data processing device includes: a processor, a data processing interface and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer execution instructions. When the point cloud data processing device is running, the processor executes the computer execution instructions stored in the memory, so that the point cloud data processing device performs the method described in any one of claims 1-3.

8. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 3.