House plan reconstruction method and device, server and computer readable storage medium

By acquiring and processing point clouds, the user-type map reconstruction model extracts multi-scale features and conducts polygon query, solving the problem of poor floor plan reconstruction effect in the existing technology, and achieving accurate description of house space information and accurate room type predict.

CN119091031APending Publication Date: 2024-12-06ZHUHAI 4DAGE TECH CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310658710.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-06
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the reconstruction effect of floor plan is poor, and it is impossible to accurately generate house space information and predict room types.

Method used

By obtaining the pending point cloud, the model is reconstructed using pre-set floor maps, including extracting multi-scale features, mapping as a top-view density map, and using the CNN backbone network and encoder decoder module to generate enhanced feature maps for polygon query and predict rooms type.

Benefits of technology

It realizes accurate generation of floor plan and accurate prediction of room type, improving the effect of floor plan reconstruction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091031A_ABST
    Figure CN119091031A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of image processing, and provides a house type image reconstruction method and device, a server and a computer readable storage medium, and the method comprises the steps: obtaining a to-be-processed point cloud which represents the space information of a house; inputting the to-be-processed point cloud into a preset house type image reconstruction model to generate a house type image; wherein the house type image comprises a plurality of room polygons and room vertexes corresponding to the room polygons, and the room polygons are marked with room types. Therefore, the house type image can be accurately generated according to the point cloud, and the polygonal room type of each room in the house type image can be predicted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of image processing technology, and in particular, relates to a floor plan reconstruction method, device, server and computer-readable storage medium. Background Art

[0002] With the development of three-dimensional digitalization, point clouds of indoor houses are used in the existing technology to reconstruct floor plans. The reconstructed floor plans can be used as the basis for many subsequent processes such as floor plan modification, three-dimensional reconstruction, and home decoration design. However, the floor plan reconstruction of the existing technology can only simply reconstruct the outline of the floor plan, but the reconstruction effect is not good. Summary of the invention

[0003] The embodiments of the present application provide a method, device, server, and computer-readable storage medium for reconstructing a floor plan, which can solve the problem of poor reconstruction effect in the prior art.

[0004] In a first aspect, an embodiment of the present application provides a method for reconstructing a floor plan, comprising: Acquire a point cloud to be processed, where the point cloud to be processed is a point cloud representing spatial information of a house; The point cloud to be processed is input into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes a plurality of room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

[0005] In a possible implementation of the first aspect, inputting the to-be-processed point cloud into a preset floor plan reconstruction model to generate a floor plan includes: Extracting multi-scale features of the point cloud to be processed; Based on a pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to the multi-scale features, and the room types corresponding to the room polygons are predicted.

[0006] In a possible implementation manner of the first aspect, extracting multi-scale features of the point cloud to be processed includes: Mapping the point cloud to be processed into a top-down density map; The multi-scale features of the bird's-eye view density map are extracted according to a pre-set CNN backbone network.

[0007] In a possible implementation of the first aspect, the pre-set floor plan reconstruction module includes an encoder and a decoder; Based on the pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to the multi-scale features, and the room types corresponding to the room polygons are predicted, including: Generating an enhanced feature map based on pixel features of the multi-scale features determined by the encoder; Based on the decoder, a two-level polygon query is performed according to the enhanced feature map to obtain multiple room polygons and room vertices corresponding to the room polygons, and label probability calculation is performed according to each room polygon and the room vertices corresponding to the room polygon to obtain the room type corresponding to the room polygon.

[0008] In a second aspect, an embodiment of the present application provides a floor plan reconstruction device, including: An acquisition module is used to acquire a point cloud to be processed, wherein the point cloud to be processed is a point cloud representing spatial information of a house; A generation module is used to input the point cloud to be processed into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes multiple room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

[0009] In a possible implementation, the generating module includes: An extraction submodule, used to extract multi-scale features of the point cloud to be processed; The query submodule is used to query multiple room polygons and room vertices corresponding to the room polygons based on the pre-set floor plan reconstruction module and the multi-scale features, and predict the room type corresponding to the room polygons.

[0010] In a possible implementation, the extraction submodule includes: A mapping unit, used for mapping the point cloud to be processed into a top-down density map; The extraction unit is used to extract the multi-scale features of the top-view density map according to a preset CNN backbone network.

[0011] In a possible implementation, the pre-set floor plan reconstruction module includes an encoder and a decoder; The query submodule comprises: A generating unit, configured to generate an enhanced feature map based on the pixel features of the multi-scale features determined by the encoder; A query unit is used to perform a two-level polygon query based on the decoder according to the enhanced feature map, obtain multiple room polygons and room vertices corresponding to the room polygons, calculate label probabilities according to each room polygon and the room vertices corresponding to the room polygon, and obtain the room type corresponding to the room polygon.

[0012] In a third aspect, an embodiment of the present application provides a server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0014] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The embodiment of the present application obtains a point cloud to be processed, which is a point cloud representing the spatial information of a house; the point cloud to be processed is input into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes multiple room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types. It can be seen that the embodiment of the present application can accurately generate a floor plan based on the point cloud, and predict the room type of each room polygon in the floor plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 is a schematic flow chart of a floor plan reconstruction method provided by the present application; Figure 2 is a schematic diagram of the structure of a floor plan reconstruction device provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of the server provided in the embodiment of the present application. Implementation

[0017] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0018] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0019] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0020] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0021] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0023] The specific scheme of the embodiment of this application is introduced below.

[0024] Figure 1 A schematic flow chart of a floor plan reconstruction method provided by the present application is shown. As an example but not a limitation, the method can be applied to a server. The method includes the following steps: Step S101, obtaining a point cloud to be processed, wherein the point cloud to be processed is a point cloud representing the spatial information of a house.

[0025] It can be understood that the point cloud to be processed is generated based on the image taken by the depth camera, and the depth camera includes an RGB camera and a laser sensor.

[0026] Specifically, an RGB-D image is obtained, and a point cloud to be processed is generated based on the RGB-D image. Among them, the RGB-D image is an image corresponding to a scene object (such as an indoor scene or an outdoor scene), and the RGB-D image includes an RGB image and a depth image. It can be understood that an RGB image refers to an image with three color channels: red, green, and blue, which are used to describe the appearance, color, and texture of a scene object; a depth image is similar to a grayscale image, and each pixel value thereof is the actual distance between the sensor and the scene object, that is, the depth value, which is used to describe the shape, scale, and geometric space of the scene object. Exemplarily, the three-dimensional coordinates of the point cloud to be processed are obtained according to the following formula: , Among them, (u, v) is the pixel coordinate of each key point in the RGB-D image, d is the depth value of each key point in the RGB-D image, K is the intrinsic parameter of the RGB camera, and (X, Y, Z) is the three-dimensional coordinate of the point cloud. It should be noted that the key point refers to the pixel point with characteristic properties in the image, and the depth value refers to the distance from the pixel point to the scene object, which can be directly obtained by the laser sensor. The intrinsic parameter can be calculated by Zhang Zhengyou calibration method.

[0027] Step S102: input the point cloud to be processed into a preset floor plan reconstruction model to generate a floor plan, wherein the floor plan includes a plurality of room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

[0028] In a possible implementation, the point cloud to be processed is input into a preset floor plan reconstruction model to generate a floor plan, including: Step S201, extracting multi-scale features of the point cloud to be processed.

[0029] In specific applications, multi-scale features of the point cloud to be processed are extracted, including: Step S301, mapping the point cloud to be processed into a top-down density map.

[0030] It can be understood that the point cloud to be processed is mapped from three-dimensional world coordinates to two-dimensional plane image coordinates.

[0031] Step S302, extracting multi-scale features of the bird's-eye view density map according to a pre-set CNN backbone network.

[0032] Among them, the pre-set CNN backbone network includes three convolutional layers and one position encoding layer.

[0033] Exemplarily, three convolutional layers are used to extract the scale features of the top-view density map respectively, and then position encoding is added to the pixel position where each scale feature is located, thereby forming a flat feature sequence, namely a multi-scale feature.

[0034] Step S202, based on a pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to multi-scale features, and the room type corresponding to the room polygon is predicted.

[0035] Among them, the pre-set floor plan reconstruction module includes an encoder and a decoder.

[0036] In the specific application, based on the pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to the multi-scale features, and the room types corresponding to the room polygons are predicted, including: Step S401, generating an enhanced feature map based on pixel features of multi-scale features determined by the encoder.

[0037] The encoder includes multiple encoding layers, each of which is composed of a multi-scale deformable self-attention module and a feed-forward network. Exemplarily, the multiple encoding layers query pixel features according to the positions of pixels of the multi-scale features and output enhanced feature maps with the same resolution.

[0038] Step S402, based on the decoder, a two-level polygon query is performed according to the enhanced feature map to obtain multiple room polygons and room vertices corresponding to the room polygons, and label probability calculation is performed according to each room polygon and the room vertices corresponding to the room polygon to obtain the room type corresponding to the room polygon.

[0039] Among them, the decoder includes multiple decoding layers, each layer includes a self-attention module, a multi-scale deformable cross-attention module and a feedforward network; in the two-level polygon query, one level is used for room polygon query and the other level is used for room vertex query.

[0040] Exemplarily, a two-level polygon query is performed based on the decoder according to the enhanced feature map to obtain multiple room polygons and room vertices corresponding to the room polygons, including: each decoding layer receives the enhanced image features from the encoder and the polygon query set of the previous layer, the polygon queries first interact with each other in the self-attention module, and in the multi-scale deformable cross-attention module, the polygon queries focus on different areas of the enhanced feature map to query multiple room polygons, and finally, the output of the decoder is passed to the shared feedforward network to predict the binary class label of each query and query the room vertices corresponding to the room polygon.

[0041] Specifically, label probability calculation is performed based on each room polygon and the room vertices corresponding to the room polygon to obtain the room type corresponding to the room polygon, including: The output of the last layer of the decoder is embedded, and the room-level features are aggregated by simply averaging the diagonal features and obtaining the aggregated embedding to form a simple linear projection layer. Finally, the softmax function is used to calculate the label probability of the room vertices and output the room type corresponding to the room polygon.

[0042] In the embodiment of the present application, by obtaining a point cloud to be processed, the point cloud to be processed is a point cloud representing the spatial information of a house; the point cloud to be processed is input into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes a plurality of room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types. It can be seen that the embodiment of the present application can accurately generate a floor plan based on the point cloud, and predict the room type of each room polygon in the floor plan.

[0043] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0044] Corresponding to the floor plan reconstruction method described in the above embodiment, Figure 2 A structural block diagram of a floor plan reconstruction device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0045] Reference Figure 2 , the device comprises: An acquisition module 21 is used to acquire a point cloud to be processed, where the point cloud to be processed is a point cloud representing spatial information of a house; The generation module 22 is used to input the point cloud to be processed into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes a plurality of room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

[0046] In a possible implementation, the generating module includes: An extraction submodule, used to extract multi-scale features of the point cloud to be processed; The query submodule is used to query multiple room polygons and room vertices corresponding to the room polygons based on the pre-set floor plan reconstruction module and the multi-scale features, and predict the room type corresponding to the room polygons.

[0047] In a possible implementation, the extraction submodule includes: A mapping unit, used for mapping the point cloud to be processed into a top-down density map; The extraction unit is used to extract the multi-scale features of the top-view density map according to a preset CNN backbone network.

[0048] In a possible implementation, the pre-set floor plan reconstruction module includes an encoder and a decoder; The query submodule comprises: A generating unit, configured to generate an enhanced feature map based on the pixel features of the multi-scale features determined by the encoder; A query unit is used to perform a two-level polygon query based on the decoder according to the enhanced feature map, obtain multiple room polygons and room vertices corresponding to the room polygons, calculate label probabilities according to each room polygon and the room vertices corresponding to the room polygon, and obtain the room type corresponding to the room polygon.

[0049] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0050] Figure 3 This is a schematic diagram of the structure of the server provided in the embodiment of the present application. Figure 3 As shown, the server 3 of this embodiment includes: at least one processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, and when the processor 30 executes the computer program 32, the steps in any of the above-mentioned method embodiments are implemented.

[0051] The server 3 may be a computing device such as a cloud server. The server may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of server 3 and does not constitute a limitation on server 3. Server 3 may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0052] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0053] In some embodiments, the memory 31 may be an internal storage unit of the server 3, such as a hard disk or memory of the server 3. In other embodiments, the memory 31 may also be an external storage device of the server 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 3. Further, the memory 31 may also include both an internal storage unit of the server 3 and an external storage device. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0054] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0055] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0056] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the server, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0057] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for reconstructing a floor plan, characterized in that: include: Acquire a point cloud to be processed, where the point cloud to be processed is a point cloud representing spatial information of a house; The point cloud to be processed is input into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes a plurality of room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

2. The method for reconstructing a floor plan according to claim 1, wherein: Inputting the to-be-processed point cloud into a preset floor plan reconstruction model to generate a floor plan, including: Extracting multi-scale features of the point cloud to be processed; Based on a pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to the multi-scale features, and the room types corresponding to the room polygons are predicted.

3. The floor plan reconstruction method according to claim 2, characterized in that: Extracting multi-scale features of the point cloud to be processed includes: Mapping the point cloud to be processed into a top-down density map; The multi-scale features of the bird's-eye view density map are extracted according to a pre-set CNN backbone network.

4. The method for reconstructing a floor plan according to claim 2, wherein: The pre-set floor plan reconstruction module includes an encoder and a decoder; Based on the pre-set floor plan reconstruction module, multiple room polygons and room vertices corresponding to the room polygons are queried according to the multi-scale features, and the room types corresponding to the room polygons are predicted, including: Generating an enhanced feature map based on pixel features of the multi-scale features determined by the encoder; Based on the decoder, a two-level polygon query is performed according to the enhanced feature map to obtain multiple room polygons and room vertices corresponding to the room polygons, and label probability calculation is performed according to each room polygon and the room vertices corresponding to the room polygon to obtain the room type corresponding to the room polygon.

5. A floor plan reconstruction device, characterized in that: include: An acquisition module is used to acquire a point cloud to be processed, wherein the point cloud to be processed is a point cloud representing spatial information of a house; A generation module is used to input the point cloud to be processed into a preset floor plan reconstruction model to generate a floor plan; wherein the floor plan includes multiple room polygons and room vertices corresponding to the room polygons, and the room polygons are marked with room types.

6. The floor plan reconstruction device according to claim 5, characterized in that: The generating module comprises: An extraction submodule, used to extract multi-scale features of the point cloud to be processed; The query submodule is used to query multiple room polygons and room vertices corresponding to the room polygons based on the pre-set floor plan reconstruction module and the multi-scale features, and predict the room type corresponding to the room polygons.

7. The floor plan reconstruction device according to claim 6, characterized in that: The extraction submodule comprises: A mapping unit, used for mapping the point cloud to be processed into a top-down density map; The extraction unit is used to extract the multi-scale features of the top-view density map according to a preset CNN backbone network.

8. The floor plan reconstruction device according to claim 6, characterized in that: The pre-set floor plan reconstruction module includes an encoder and a decoder; The query submodule includes: A generating unit, configured to generate an enhanced feature map based on the pixel features of the multi-scale features determined by the encoder; A query unit is used to perform a two-level polygon query based on the decoder according to the enhanced feature map, obtain multiple room polygons and room vertices corresponding to the room polygons, calculate label probabilities according to each room polygon and the room vertices corresponding to the room polygon, and obtain the room type corresponding to the room polygon.

9. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.