Indoor structure modeling method and system based on laser point cloud data

By slicing and plane projecting the laser point cloud data, the indoor planar structure and building height information are extracted, and the problem of low indoor three-dimensional modeling efficiency in the existing technology is solved, and efficient indoor three-dimensional modeling is achieved, providing intelligent surveying Have a good data foundation.

CN118916953APending Publication Date: 2024-11-08CHINA RAILWAY FIRST SURVEY & DESIGN INST GRP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410915893.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing three-dimensional indoor modeling method based on laser point cloud data is inefficient, labor intensity and labor cost, making it difficult to apply to indoor scenarios of different types and structures.

Method used

By slicing the laser point cloud data in the horizontal and vertical directions, it is projected to a two-dimensional plane to extract the indoor plan structure, and combined with the height information of each floor of the building, it is carried out for three-dimensional modeling, which simplifies the modeling process and improves efficiency .

Benefits of technology

It realizes three-dimensional indoor modeling with simple operation and high modeling efficiency, providing good basic data for interior design, navigation and roaming.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916953A_ABST
    Figure CN118916953A_ABST
Patent Text Reader

Abstract

The invention discloses an indoor structure modeling method and system based on laser point cloud data, and the method comprises the steps: carrying out the slicing and plane projection of the point cloud data of each indoor layer, filtering a large amount of redundant information through the point cloud slicing and two-dimensional projection, drawing an indoor two-dimensional structure based on an indoor horizontal plane projection result, and analyzing the layer height according to the indoor vertical slicing point cloud. Finally, indoor plane structure data are imported into modeling software, indoor structure three-dimensional modeling is carried out in combination with the floor height, compared with a traditional reverse modeling method, operation is easy, the modeling efficiency is high, and good basic data are provided for subsequent indoor design, indoor roaming and navigation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of indoor three-dimensional modeling, and in particular to an indoor structure modeling method and system based on laser point cloud data. Background Art

[0002] With the continuous development of smart cities and BIM, indoor 3D modeling has gradually received attention from the engineering industry. Indoor structural models have important applications in indoor design, indoor navigation, indoor emergency rescue, etc. In recent years, laser LiDAR technology has been widely used in the acquisition of indoor structural point cloud data. Laser LiDAR scanners can obtain massive, complete, and high-precision point cloud data of indoor scenes through mobile platforms such as handheld, backpacks, carts, and robots. It provides a good data source for indoor 3D modeling. Indoor structure reverse modeling based on laser point cloud data has become the mainstream solution for indoor 3D reconstruction. Although many scholars have proposed fully automatic modeling methods for indoor structures based on laser point cloud data, these methods have poor universality and are difficult to apply to indoor scenes of different types and structures. Therefore, in actual production, most of them use modeling software (such as 3dmax and sketchup software) for manual modeling.

[0003] Regardless of which modeling software is used, the current process of indoor 3D modeling based on laser point cloud data is generally to directly import the point cloud data into the modeling software, and manually model indoor structures such as walls, floors, windows, etc. according to the point cloud position. This direct modeling method in three-dimensional space is inefficient, labor-intensive, and has high labor costs, and can no longer meet the current needs of intelligent surveying. Summary of the invention

[0004] The present application provides a method and system for indoor structure modeling based on laser point cloud data to solve the problem that the traditional method of directly importing point cloud data into modeling software and manually modeling indoor structures such as walls, floors, windows, etc. according to the point cloud positions is low in efficiency, labor-intensive, and has high labor costs.

[0005] According to the first aspect, an embodiment provides a method for indoor structure modeling based on laser point cloud data, the method comprising:

[0006] Collecting indoor laser point cloud data and performing point cloud slicing processing on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices;

[0007] Projecting the horizontal point cloud slice onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the grayscale value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel;

[0008] Extracting the indoor plane structure based on the two-dimensional projection image, and drawing an indoor plane structure diagram;

[0009] The height information of each floor of the building is obtained based on the vertical point cloud slices, and the indoor three-dimensional model is obtained by performing three-dimensional modeling based on the indoor plan structure diagram and the height information of each floor of the building.

[0010] Furthermore, the laser point cloud data is subjected to point cloud slicing processing in the horizontal direction and the vertical direction, specifically including:

[0011] Each layer of indoor point cloud is sliced ​​along the horizontal plane direction, and the indoor point cloud is sliced ​​along the vertical plane direction.

[0012] Furthermore, the horizontal point cloud slice is projected onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the grayscale value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel, specifically including:

[0013] The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel.

[0014] Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe;

[0015] The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows:

[0016] Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,y max ;

[0017] According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image:

[0018]

[0019] Calculate the gray value I of each pixel q in the two-dimensional image q , I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

[0020]

[0021] Further, extracting the indoor plane structure based on the two-dimensional projection image and drawing the indoor plane structure diagram specifically includes:

[0022] The indoor plane structure is manually extracted by manual drawing method, and the point cloud two-dimensional projection image is imported into the drawing software to manually draw the indoor structure and draw the plane structure diagram.

[0023] Further, obtaining the height information of each floor of the building based on the vertical point cloud slices specifically includes:

[0024] The height of each floor of the building is determined by measuring the vertical slice point cloud.

[0025] Further, three-dimensional modeling is performed based on the indoor plane structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model, which specifically includes:

[0026] Data import: import the indoor plan structure diagram into the 3D modeling software;

[0027] Determination of coordinate system and coordinate origin: The coordinate system needs to be set in the modeling software to assist modeling. The principle of setting the coordinate system is to facilitate modeling. The coordinate origin is consistent with the origin of the plane structure diagram. The coordinate system consists of the X-axis, Y-axis and Z-axis. First, determine the X-axis and Y-axis and their directions. The plane where the X-axis and Y-axis are located is consistent with the indoor plane structure diagram. The Z-axis is perpendicular to the plane where the X-axis and Y-axis are located, forming a right-handed coordinate system, which is automatically determined by the direction of the X-axis and Y-axis.

[0028] Indoor hierarchical structure modeling: Structural modeling is performed on each floor plan of the interior imported into the modeling software. According to the structural base map and floor height, the cover tool and push-pull tool are used to quickly build the wall structure and establish the indoor structure model framework;

[0029] Component construction and placement: After building the indoor structural model, you need to build the indoor components; the style and size of the components should be consistent with the actual situation. The modeling software has a dynamic component function, that is, the size of the component is controlled by the component parameters; after the components are made, they are accurately placed in the appropriate position indoors according to the information in the structural diagram;

[0030] Texture mapping: The modeling software comes with a material library. You can use the materials in the material library or make your own materials by taking photos to perform texture mapping on the components of the indoor three-dimensional scene.

[0031] According to the second aspect, an embodiment provides an indoor structure modeling system based on laser point cloud data, the system comprising:

[0032] A point cloud slicing module is used to collect indoor laser point cloud data and perform point cloud slicing processing on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices;

[0033] A point cloud plane projection module, used to project the horizontal point cloud slice onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the gray value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel;

[0034] An indoor plane structure drawing module is used to extract the indoor plane structure based on the two-dimensional projection image and draw the indoor plane structure diagram;

[0035] The indoor three-dimensional modeling module is used to obtain the height information of each floor of the building based on the vertical point cloud slices, and to perform three-dimensional modeling based on the indoor plan structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model.

[0036] Furthermore, the point cloud plane projection module is specifically used for:

[0037] The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel.

[0038] Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe;

[0039] The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows:

[0040] Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,y max ;

[0041] According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image:

[0042]

[0043] Calculate the gray value I of each pixel q in the two-dimensional image q , I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

[0044]

[0045] According to a third aspect, an embodiment provides an electronic device, the device comprising: a processor and a memory;

[0046] The memory is used to store one or more program instructions;

[0047] The processor is used to run one or more program instructions to execute the steps of the indoor structure modeling method based on laser point cloud data as described in any one of the above items.

[0048] According to the fourth aspect, an embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for indoor structure modeling based on laser point cloud data as described in any one of the above items are implemented.

[0049] The present application provides a method and system for modeling indoor structures based on laser point cloud data, which slices and plane-projects the point cloud data of each layer indoors, filters out a large amount of redundant information through point cloud slicing and two-dimensional projection, draws the indoor two-dimensional structure based on the indoor horizontal plane projection result, analyzes the floor height according to the indoor vertical slice point cloud, and finally imports the indoor plane structure data into the modeling software, and performs three-dimensional modeling of the indoor structure in combination with the floor height. Compared with the traditional reverse modeling method, the present invention is simple to operate and has a higher modeling efficiency, and provides better basic data for subsequent indoor design, indoor roaming and navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a method for indoor structure modeling based on laser point cloud data provided by one embodiment of the present invention;

[0051] Figure 2 An overall framework flow chart of an indoor structure modeling method based on laser point cloud data provided by an embodiment of the present invention;

[0052] Figure 3 An example of horizontal and vertical slicing results of a point cloud in a method for indoor structure modeling based on laser point cloud data provided by an embodiment of the present invention;

[0053] Figure 4 An example of point cloud plane projection results in a method for indoor structure modeling based on laser point cloud data provided by an embodiment of the present invention;

[0054] Figure 5 An example of indoor plane structure drawing results in an indoor structure modeling method based on laser point cloud data provided by an embodiment of the present invention;

[0055] Figure 6 An example of indoor structure three-dimensional modeling results in an indoor structure modeling method based on laser point cloud data provided by an embodiment of the present invention;

[0056] Figure 7 A schematic diagram of the logical structure of an indoor structure modeling system based on laser point cloud data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0058] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0059] The first embodiment of the present invention provides an indoor structure modeling method based on laser point cloud data. The overall framework process of the present invention is as follows Figure 1 and Figure 2 As shown in the figure, firstly, the indoor point cloud is sliced ​​along the horizontal and vertical directions respectively, and the massive point cloud after stratification is projected onto a two-dimensional plane using the point cloud projection algorithm to complete the 3D to 2D conversion. The indoor plane structure diagram is drawn based on the 2D projection result of the horizontal plane slice point cloud, and the house floor height, window position, etc. are analyzed based on the vertical plane slice point cloud to supplement the indoor plane structure information. Finally, the indoor 3D modeling is completed based on the complete indoor plane structure and floor height. Figure 1 and Figure 2 Provide detailed explanation.

[0060] like Figure 1As shown, in step S100, indoor laser point cloud data is collected and point cloud slicing processing is performed on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices.

[0061] Indoor 3D modeling focuses on the plane structure information of the building, but the original laser point cloud data contains too much interference information, such as noise, moving objects, furniture, etc. In order to filter out unnecessary redundant information and extract the indoor structure more clearly, each layer of indoor point cloud data is sliced ​​along the horizontal plane, and the indoor point cloud is sliced ​​along the vertical plane. Based on the vertical plane slice point cloud, the building floor height, window position, etc. are analyzed to supplement the indoor plane structure information, and the indoor structure is extracted and modeled based on the sliced ​​point cloud. The results of slicing in the horizontal and vertical plane directions are shown in the figure. Figure 3 shown.

[0062] like Figure 1 As shown, in step S200, the horizontal point cloud slice is projected onto a two-dimensional plane to obtain a two-dimensional projection image, and the grayscale value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel.

[0063] In order to visualize and analyze the indoor structure more intuitively, the point cloud projection algorithm is used to project the indoor horizontal slice 3D point cloud data onto a 2D plane to generate a 2D image. The coordinates and intensity value of each point in the horizontal slice point cloud are read, and the horizontal slice point cloud is projected onto a 2D plane to form an intensity image. The image grayscale value is the average intensity of the point cloud falling into each pixel grid. Based on the intensity image, the 2D plane structure of each layer of the room can be intuitively analyzed and extracted.

[0064] The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel.

[0065] Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe;

[0066] The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows:

[0067] Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,ymax ;

[0068] According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image:

[0069]

[0070] Calculate the gray value I of each pixel q in the two-dimensional image q , I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

[0071]

[0072] The two-dimensional intensity image after the point cloud plane projection is as follows Figure 4 shown.

[0073] like Figure 1 As shown, in step S300, the indoor plane structure is extracted based on the two-dimensional projection image, and an indoor plane structure diagram is drawn.

[0074] Based on the plane projection results of the horizontal slice point cloud, the indoor plane structure can be intuitively analyzed and the plane structure diagram can be drawn. Although there are relevant artificial intelligence algorithms for intelligent recognition of image structure, such methods are not robust and have low accuracy. They are difficult to adapt to the high-precision intelligent recognition of the structural information of the point cloud projection image of any scene and require manual modification. Therefore, in order to ensure the accuracy of indoor structure modeling, the manual drawing method is used to manually extract the indoor plane structure, and the two-dimensional projection image of the point cloud is imported into the drawing software for manual drawing of the indoor structure and drawing of the plane structure. The plane structure drawing result is shown in the figure below. Figure 5 In addition to the plane structure information, indoor 3D modeling also requires the height information of each floor of the building. The height of each floor of the building is determined by measuring the vertical surface slice point cloud.

[0075] like Figure 1 As shown, in step S400, the height information of each floor of the building is obtained based on the vertical point cloud slices, and three-dimensional modeling is performed based on the indoor plan structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model.

[0076] Based on the indoor plan structure diagram and floor height information, you can use 3D modeling software to perform indoor structure 3D modeling. The main steps include data import, coordinate system and coordinate origin determination, indoor hierarchical structure modeling, component construction and placement, and texture mapping. The specific modeling steps are as follows:

[0077] (1) Data import

[0078] Import the building plan into the 3D modeling software.

[0079] (2) Determination of coordinate system and coordinate origin

[0080] The coordinate system needs to be set in the modeling software to assist in modeling. The principle of setting the coordinate system is to facilitate modeling. The origin of the coordinate is generally consistent with the origin of the plane structure diagram. The coordinate system consists of the X-axis, Y-axis and Z-axis. First determine the X-axis and Y-axis and their directions. Generally, the plane where the X-axis and Y-axis are located is consistent with the indoor two-dimensional plane diagram. The Z-axis is perpendicular to the plane where the X-axis and Y-axis are located, forming a right-handed coordinate system, which is automatically determined by the direction of the X-axis and Y-axis.

[0081] (3) Indoor hierarchical structure modeling

[0082] Structural modeling is performed separately for the indoor floor plans imported into the modeling software. According to the structural base map and floor height, cover tools and push-pull tools are used to quickly build wall structures and establish the indoor structural model framework.

[0083] (4) Component construction and placement

[0084] After building the indoor structure model, you need to build components such as doors and windows. The style and size of the components should be consistent with the actual situation. Most modeling software has a dynamic component function, that is, the size of the component is controlled by parameters such as length, width, and height. After the components are made, the doors, windows and other components are accurately placed in the appropriate position according to the information in the structure diagram.

[0085] (5) Texture Mapping

[0086] Most modeling software comes with its own material library. You can use the materials in the material library or make your own materials by taking photos to texture the components of the indoor three-dimensional scene to make it more realistic.

[0087] After the above steps, a relatively complete indoor 3D model can be constructed. The modeling results are as follows: Figure 6 shown.

[0088] An embodiment of the present invention provides an indoor structure modeling method based on laser point cloud data, which slices and plane-projects the point cloud data of each layer indoors, filters out a large amount of redundant information through point cloud slicing and two-dimensional projection, draws the indoor two-dimensional structure based on the indoor horizontal plane projection result, analyzes the floor height according to the indoor vertical slice point cloud, and finally imports the indoor plane structure data into the modeling software, and performs three-dimensional modeling of the indoor structure in combination with the floor height. Compared with the traditional reverse modeling method, the present invention is simple to operate and has a higher modeling efficiency, and provides better basic data for subsequent indoor design, indoor roaming and navigation.

[0089] Corresponding to the above-disclosed indoor structure modeling method based on laser point cloud data, the embodiment of the present invention further discloses an indoor structure modeling system based on laser point cloud data, such as Figure 7 As shown, it specifically includes:

[0090] A point cloud slicing module is used to collect indoor laser point cloud data and perform point cloud slicing processing on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices;

[0091] A point cloud plane projection module, used to project the horizontal point cloud slice onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the gray value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel;

[0092] An indoor plane structure drawing module is used to extract the indoor plane structure based on the two-dimensional projection image and draw the indoor plane structure diagram;

[0093] The indoor three-dimensional modeling module is used to obtain the height information of each floor of the building based on the vertical point cloud slices, and to perform three-dimensional modeling based on the indoor plan structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model.

[0094] Furthermore, the point cloud plane projection module is specifically used for:

[0095] The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel.

[0096] Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe;

[0097] The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows:

[0098] Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,y max ;

[0099] According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image:

[0100]

[0101]

[0102] Calculate the gray value I of each pixel q in the two-dimensional image q, I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

[0103]

[0104] It should be noted that for the detailed description of an indoor structure modeling system based on laser point cloud data provided in an embodiment of the present invention, reference can be made to the relevant description of an indoor structure modeling method based on laser point cloud data provided in an embodiment of the present application, which will not be repeated here.

[0105] In addition, an embodiment of the present invention also provides an electronic device, comprising: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a method for indoor structure modeling based on laser point cloud data as described in any of the above items.

[0106] It should be noted that, for the detailed description of an electronic device provided in an embodiment of the present invention, reference can be made to the relevant description of an indoor structure modeling method based on laser point cloud data provided in an embodiment of the present application, which will not be repeated here.

[0107] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for indoor structure modeling based on laser point cloud data as described in any of the above items are implemented.

[0108] It should be noted that, for a detailed description of a computer-readable storage medium provided in an embodiment of the present invention, reference can be made to the relevant description of an indoor structure modeling method based on laser point cloud data provided in an embodiment of the present application, which will not be repeated here.

[0109] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0110] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A method for indoor structure modeling based on laser point cloud data, It is characterized in that The method comprises: Collecting indoor laser point cloud data and performing point cloud slicing processing on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices; Projecting the horizontal point cloud slice onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the grayscale value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel; Extracting the indoor plane structure based on the two-dimensional projection image, and drawing an indoor plane structure diagram; The height information of each floor of the building is obtained based on the vertical point cloud slices, and the indoor three-dimensional model is obtained by performing three-dimensional modeling based on the indoor plan structure diagram and the height information of each floor of the building.

2. A method for indoor structure modeling based on laser point cloud data as claimed in claim 1, It is characterized in that The laser point cloud data is subjected to point cloud slicing processing in the horizontal direction and the vertical direction, specifically comprising: Each layer of indoor point cloud is sliced ​​along the horizontal plane direction, and the indoor point cloud is sliced ​​along the vertical plane direction.

3. The indoor structure modeling method based on laser point cloud data according to claim 1, It is characterized in that The horizontal point cloud slice is projected onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the gray value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel, specifically including: The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel. Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe; The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows: Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,y max ; According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image: Calculate the gray value I of each pixel q in the two-dimensional image q , I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

4. The indoor structure modeling method based on laser point cloud data according to claim 1, It is characterized in that Extracting the indoor plane structure based on the two-dimensional projection image and drawing the indoor plane structure diagram specifically includes: The indoor plane structure is manually extracted by manual drawing method, and the point cloud two-dimensional projection image is imported into the drawing software to manually draw the indoor structure and draw the plane structure diagram.

5. The indoor structure modeling method based on laser point cloud data according to claim 1, It is characterized in that Acquiring the height information of each floor of the building based on the vertical point cloud slices specifically includes: The height of each floor of the building is determined by measuring the vertical slice point cloud.

6. The indoor structure modeling method based on laser point cloud data according to claim 1, It is characterized in that The three-dimensional modeling is performed based on the indoor plane structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model, specifically including: Data import: import the indoor plan structure diagram into the 3D modeling software; Determination of coordinate system and coordinate origin: The coordinate system needs to be set in the modeling software to assist modeling. The principle of setting the coordinate system is to facilitate modeling. The coordinate origin is consistent with the origin of the plane structure diagram. The coordinate system consists of the X-axis, Y-axis and Z-axis. First, determine the X-axis and Y-axis and their directions. The plane where the X-axis and Y-axis are located is consistent with the indoor plane structure diagram. The Z-axis is perpendicular to the plane where the X-axis and Y-axis are located, forming a right-handed coordinate system, which is automatically determined by the direction of the X-axis and Y-axis. Indoor hierarchical structure modeling: Structural modeling is performed on each floor plan of the interior imported into the modeling software. According to the structural base map and floor height, the cover tool and push-pull tool are used to quickly build the wall structure and establish the indoor structure model framework; Component construction and placement: After building the indoor structural model, you need to build the indoor components; the style and size of the components should be consistent with the actual situation. The modeling software has a dynamic component function, that is, the size of the component is controlled by the component parameters; after the components are made, they are accurately placed in the appropriate position indoors according to the information in the structural diagram; Texture mapping: The modeling software comes with a material library. You can use the materials in the material library or make your own materials by taking photos to perform texture mapping on the components of the indoor three-dimensional scene.

7. An indoor structure modeling system based on laser point cloud data, It is characterized in that The system comprises: A point cloud slicing module is used to collect indoor laser point cloud data and perform point cloud slicing processing on the laser point cloud data in horizontal and vertical directions to obtain horizontal point cloud slices and vertical point cloud slices; A point cloud plane projection module, used to project the horizontal point cloud slice onto a two-dimensional plane to obtain a two-dimensional projection image, wherein the gray value of each pixel in the two-dimensional projection image is the average intensity of the point cloud in the grid corresponding to the pixel; An indoor plane structure drawing module is used to extract the indoor plane structure based on the two-dimensional projection image and draw the indoor plane structure diagram; The indoor three-dimensional modeling module is used to obtain the height information of each floor of the building based on the vertical point cloud slices, and to perform three-dimensional modeling based on the indoor plan structure diagram and the height information of each floor of the building to obtain an indoor three-dimensional model.

8. The indoor structure modeling system based on laser point cloud data according to claim 7, It is characterized in that The point cloud plane projection module is specifically used for: The projection principle is to divide the point cloud area into regular grids, each grid corresponds to a pixel in the two-dimensional image, and the gray value of each pixel is the average reflection intensity of the point cloud in the grid corresponding to the pixel. Read the coordinates and intensity values ​​of each point in the horizontal slice point cloud. Each laser point p uses the spatial coordinates (x p ,y p , z p ) and intensity information p describe; The projection plane used is the XOY plane, and the grayscale value of the two-dimensional image uses the average intensity value of the point cloud. The projection steps are as follows: Traverse the plane coordinates (x p ,y p ), get the point cloud plane range x min 、x max ,y min ,y max ; According to the two-dimensional image sampling resolution s, determine the rows h and columns w of the two-dimensional image: Calculate the gray value I of each pixel q in the two-dimensional image q , I q is the average value of the point cloud intensity falling into pixel q, and the calculation formula is as follows:

9. An electronic device, It is characterized in that The device comprises: a processor and a memory; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute the steps of the indoor structure modeling method based on laser point cloud data as described in any one of claims 1 to 6.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the indoor structure modeling method based on laser point cloud data as described in any one of claims 1 to 6 are implemented.