House type map corresponding effect picture matching method, device, system and storage medium

Abstract

The application provides a matching method, device and system of a house type drawing and an effect drawing, and a storage medium. The method comprises the following steps: obtaining a 2D house type drawing, and converting each independent space region in the 2D house type drawing into house type vector data; extracting house feature information in the house type vector data, and constructing a feature sample drawing based on the house feature information; comparing the feature sample drawing with a feature index drawing; extracting a feature index drawing with the highest matching degree, and obtaining an effect drawing corresponding to the feature index drawing. The method provided by the application realizes the matching association and retrieval between the 2D house type drawing and the effect drawing, enables the 2D house type drawing and the effect drawing to establish bridge data related to each other according to the human brain thought, avoids the defects of manual page-by-page searching and looking up, improves the matching searching efficiency and accuracy, and provides support for pushing services, data statistics, garbage data elimination and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, more particularly, to a matching method, device and system for a house type drawing corresponding to an effect drawing, and a storage medium. BACKGROUND

[0002] A house type drawing is a planar space layout drawing of a house, that is, a drawing describing the use function, corresponding position and size of each independent space. The layout of the house can be intuitively understood. An effect drawing is a high-fidelity virtual picture simulating a real environment by using computer three-dimensional simulation software technology. An interior design effect drawing, that is, a single-eye RGB interior decoration effect drawing, is a form in which an interior designer expresses creative ideas and visualizes the creative ideas by using 3D effect drawing making software. The interior design effect drawing faithfully represents the shape, structure, color, texture and other factors of an object, truly visualizes the creative ideas of the designer, thereby communicating the visual language between the designer and the viewer and enabling people to more clearly understand the performance, structure and materials of the design.

[0003] After providing a house type drawing, if a corresponding interior design effect drawing after decoration is needed, a designer needs to design and render the house type drawing step by step. However, if a similar effect drawing of the house type is available in a previous inventory, the effect drawing can be directly found.

[0004] 2D house type drawings and effect drawings are two kinds of data having essential differences. It is difficult to establish a connection for matching between the two kinds of data by using a conventional method. As for finding a corresponding effect drawing for a 2D house type drawing, that is, matching a 2D house type drawing with an effect drawing, currently, only manual searching can be used, which is time-consuming, laborious, low in efficiency and accuracy. SUMMARY

[0005] Therefore, the present application provides a matching method for a house type drawing corresponding to an effect drawing, which comprises the following steps.

[0006] Obtaining a 2D house type drawing and converting each independent space region in the 2D house type drawing into corresponding house type vector data.

[0007] Extracting house feature information in the house type vector data and constructing a corresponding feature sample drawing based on the house feature information.

[0008] Comparing the feature sample drawing with feature index drawings in a preset feature library.

[0009] Extracting a feature index drawing having the highest matching degree and obtaining an effect drawing corresponding to the feature index drawing as a matching result corresponding to the independent space region in the 2D house type drawing.

[0010] Preferably, the house feature information in the house type vector data is extracted, and a corresponding feature sample graph is constructed based on the house feature information, comprising:

[0011] The spatial features and house type features in the house feature information of the house type vector data are obtained;

[0012] According to the spatial features and the house type features, the feature sample graph corresponding to the house type vector data is constructed.

[0013] Preferably, the spatial features include wall thickness, wall angle, wall size and proportion;

[0014] The house type features include window position, window features, door direction and door position.

[0015] Preferably, before the 2D house type graph is obtained and each independent space region in the 2D house type graph is converted into corresponding house type vector data, it further comprises:

[0016] The effect graph in the feature library is obtained, the effect graph is semantically segmented, and the effect graph is converted into a corresponding effect vector graph;

[0017] Based on the segmentation result of the semantic segmentation, the feature index graph is constructed according to the effect vector graph, the corresponding relationship between the feature index graph and the effect graph is established, and the feature index graph is stored in the feature library.

[0018] Preferably, the effect graph is semantically segmented, and the effect graph is converted into a corresponding effect vector graph, comprising:

[0019] Using the trained recognition model, the element feature information in the effect graph is extracted as the segmentation result based on the semantic segmentation algorithm;

[0020] The effect graph is fitted into a corresponding effect vector graph.

[0021] Preferably, the effect graph is fitted into a corresponding effect vector graph, comprising:

[0022] The pixel vector data of the effect graph is extracted;

[0023] According to the pixel vector data and the segmentation result, the effect graph is fitted into the effect vector graph of the top view angle.

[0024] Preferably, the pixel vector data of the effect graph is extracted, comprising:

[0025] The wall corner point features in the effect graph are extracted;

[0026] According to the wall corner point feature, the number of walls in the effect drawing and the distance relationship and adjacent relationship of the walls are acquired, and the number of walls, the distance relationship of the walls and the adjacent relationship of the walls are taken as the pixel vector data.

[0027] In addition, to solve the above problems, the application further provides a 2D house type drawing corresponding effect drawing matching device, comprising:

[0028] An acquisition module is configured to acquire a 2D house type drawing and convert each independent space region in the 2D house type drawing into corresponding house type vector data.

[0029] An extraction module is configured to extract house feature information in the house type vector data and construct a corresponding feature sample drawing based on the house feature information.

[0030] A comparison module is configured to compare the feature sample drawing with feature index drawings in a preset feature library.

[0031] The extraction module is further configured to extract the feature index drawing with the highest matching degree and acquire an effect drawing corresponding to the feature index drawing as a matching result corresponding to the independent space region in the 2D house type drawing.

[0032] In addition, to solve the above problems, the application further provides a 2D house type drawing corresponding effect drawing matching system, comprising a memory and a processor, the memory is configured to store a 2D house type drawing corresponding effect drawing matching program, and the processor is configured to run the 2D house type drawing corresponding effect drawing matching program to enable the 2D house type drawing corresponding effect drawing matching system to perform the house type drawing corresponding effect drawing matching method as described above.

[0033] In addition, to solve the above problems, the application further provides a computer readable storage medium, the computer readable storage medium stores a 2D house type drawing corresponding effect drawing matching program, and the 2D house type drawing corresponding effect drawing matching program is executed by a processor to implement the house type drawing corresponding effect drawing matching method as described above.

[0034] This invention provides a method, apparatus, system, and storage medium for matching floor plans with corresponding renderings. The method includes: acquiring a 2D floor plan and converting each independent spatial region in the 2D floor plan into corresponding floor plan vector data; extracting house feature information from the floor plan vector data and constructing a corresponding feature sample map based on the house feature information; comparing the feature sample map with feature index maps in a preset feature library; extracting the feature index map with the highest matching degree and obtaining the rendering corresponding to the feature index map as the matching result with the independent spatial region in the 2D floor plan. The method provided by this invention converts the acquired 2D floor plan into floor plan vector data, extracts house feature information and constructs a feature sample map, and then matches it with the feature index map in the feature library. The method selects the rendering corresponding to the feature index map with the highest matching degree, realizing the matching association and retrieval between 2D floor plans and renderings. This allows 2D floor plans and renderings to establish a data bridge of association in accordance with human thinking, avoiding the defects of manual searching one by one, improving the efficiency and accuracy of matching and searching, and providing support for push services, data statistics, and garbage data removal, etc. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the hardware operating environment involved in an embodiment of the method for matching floor plans with renderings according to the present invention.

[0036] Figure 2 This is a flowchart illustrating the first embodiment of the method for matching floor plans with renderings according to the present invention.

[0037] Figure 3 This is a detailed flowchart of step S200 in the second embodiment of the method for matching floor plans with renderings according to the present invention.

[0038] Figure 4 This is a flowchart illustrating the third embodiment of the method for matching floor plans with renderings according to the present invention.

[0039] Figure 5 This is a detailed flowchart of step S500 in the third embodiment of the method for matching floor plans with renderings according to the present invention.

[0040] Figure 6 This is a detailed flowchart of step S520 in the third embodiment of the method for matching floor plans with renderings according to the present invention.

[0041] Figure 7 This is a detailed flowchart of step S521 in the third embodiment of the method for matching floor plans with renderings according to the present invention.

[0042] Figure 8A module connection schematic diagram of the matching device of the 2D house type drawing and corresponding effect drawing of the present application.

[0043] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0044] Embodiments of the present application are described below in detail, in which the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout.

[0045] In addition, the terms "first", "second" are only used for descriptive purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified and limited.

[0046] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting", "fixing" and the like should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integral; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0047] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0048] As shown in Figure 1 is a structural schematic diagram of the hardware running environment of the terminal related to the embodiments of the present application.

[0049] The 2D house type drawing corresponding effect drawing matching system can be a PC, a smart phone, a tablet computer, a portable computer or a movable terminal device. The 2D house type drawing corresponding effect drawing matching system can include a processor 1001, for example, a CPU, a network interface 1004, a user interface 1003, a memory 1005 and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display screen, an input unit such as a keyboard, a remote controller, and an optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 can be a high-speed RAM memory or a stable memory such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001. Optionally, the 2D house type drawing corresponding effect drawing matching system can also include an RF (Radio Frequency, RF) circuit, an audio circuit, a WiFi module and the like. In addition, the 2D house type drawing corresponding effect drawing matching system can also be configured with a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor and other sensors, which will not be described here.

[0050] Those skilled in the art can understand that Figure 1 The 2D house type drawing corresponding effect drawing matching system shown in the above embodiments does not constitute a limitation thereon, and can include more or fewer components than shown, or combine certain components, or different component arrangements. For example, Figure 1 As a computer readable storage medium, the memory 1005 can include an operating system, a data interface control program, a network connection program and a 2D house type drawing corresponding effect drawing matching program.

[0051] The present application provides a house type drawing corresponding effect drawing matching method, device, system and storage medium. The method realizes the matching association and retrieval between the 2D house type drawing and the effect drawing, so that the 2D house type drawing and the effect drawing can establish relevant bridge data according to the human brain thought on the data, avoid the defects of manual browsing and searching one by one, improve the matching and searching efficiency and accuracy, and provide support for push service, data statistics, garbage data removal and the like.

[0052] Embodiment 1:

[0053] Referring to Figure 2 The first embodiment of the present application provides a house type drawing corresponding effect drawing matching method, comprising:

[0054] In step S100, a 2D house type drawing is obtained, and each independent space region in the 2D house type drawing is converted into corresponding house type vector data.

[0055] The above-mentioned 2D house type diagram is a top view of a house type structure, which can be a house type structure composed of lines, and is usually a house type diagram file created by CAD.

[0056] The above-mentioned independent space region is a number of separate rooms or space regions contained in the 2D house type diagram. For example, a 2D house type diagram of a three-room and one-living-room room includes eight independent spaces: one bathroom, one balcony, one bathroom, one living room, three rooms, and one kitchen. Each independent space is an independent space region.

[0057] The above-mentioned house type diagram can include at least one independent space region.

[0058] The house type vector data is a collection of data in the form of a vector diagram based on the structural features of a house type diagram, which can include features on the house type structure, such as, but not limited to, wall position, shape, thickness, or size, as well as space size, room structure, door and window position, furniture position, and the like.

[0059] In step S200, the house feature information in the house type vector data is extracted, and a corresponding feature sample diagram is constructed based on the house feature information.

[0060] The above-mentioned house feature information is the structure, shape, size, and the like of the house in the house type vector data. Based on these features, a corresponding feature sample diagram is constructed.

[0061] The above-mentioned feature sample diagram is a vector diagram corresponding to an independent space region, which can display part or all of the structure and house type features of the region.

[0062] According to the house feature information, a feature sample diagram of the independent space region can be constructed, which contains all or part of the features of the independent space region and can be used for graphical quick matching and retrieval.

[0063] In step S300, the feature sample diagram is compared with a feature index diagram in a preset feature library.

[0064] The above-mentioned feature library is a collection of data of effect diagrams and feature index diagrams collected and stored in advance. It includes effective diagrams and feature index diagrams corresponding to each effect diagram.

[0065] The above-mentioned feature index diagram is also a vector diagram, which can contain the basic graphical features in the effect diagram that can be used for retrieval and matching. Since the feature index diagram corresponds to the effect diagram, it is equivalent to the index of the effect diagram in the feature library for retrieval and matching.

[0066] Step S400, extract the feature index map with the highest matching degree, and obtain the effect map corresponding to the feature index map as the matching result corresponding to the independent space region in the 2D house type map.

[0067] In the above matching process, by searching for multiple feature index maps in the feature library, in this embodiment, in order to find the most accurate search result, each searched feature index map is sorted according to the matching degree obtained after comparing with the feature sample map, the feature index map with the highest matching degree is selected, and then the effect map corresponding to the feature index map is extracted according to the corresponding relationship. The effect map is the final matching result.

[0068] Therefore, in this embodiment, the main process includes: "2D house type map" - "house type vector data" - "feature index map" - "effect map", thereby realizing the search and matching process from the 2D house type map to the effect map, and thus realizing the search of the house type map to the effect map in the feature library.

[0069] The method provided by the embodiment converts the obtained 2D house type map into house type vector data, extracts house feature information and constructs a feature sample map, and then matches the feature index map in the feature library, selects the effect map corresponding to the feature index map with the highest matching degree, realizes the matching association and search between the 2D house type map and the effect map, and makes the 2D house type map and the effect map be associated with bridge data according to the human brain thought on the data. Avoid the defects of manual search one by one, improve the matching search efficiency and accuracy, and provide support for push service, data statistics, garbage data removal and the like.

[0070] Embodiment 2:

[0071] Referring to Figure 3 The second embodiment of the present application provides a matching method of house type map corresponding effect map, based on the above embodiment 1, the step S200, extracts the house feature information in the house type vector data, and constructs the corresponding feature sample map based on the house feature information, including:

[0072] Step S210, obtaining the space feature and house type feature in the house feature information of the house type vector data;

[0073] As described above, the space feature corresponds to the feature of the space function area in the house type vector data, and the house type feature is the feature of the house type function area in the house type vector data.

[0074] Step S220, constructing the feature sample map corresponding to the house type vector data according to the space feature and the house type feature.

[0075] Furthermore, the spatial features include wall thickness, wall angle, wall size, and proportion;

[0076] The apartment layout features include window location, window features, door orientation, and door location.

[0077] The aforementioned feature sample image is a vector graphic converted from an independent spatial area in a 2D apartment layout. This graphic contains basic features extracted from the apartment layout vector data, including wall thickness, wall angles, wall dimensions and proportions, window positions, window features, door orientation, and door positions.

[0078] In this embodiment, during retrieval, feature sample images containing spatial and floor plan features are further retrieved and matched with feature index images. This enables the establishment of a retrieval-enabled association between 3D or depth-of-field renderings and 2D floor plans, thereby achieving further retrieval matching, improving matching efficiency, and enhancing retrieval accuracy.

[0079] Example 3:

[0080] Reference Figure 4 The third embodiment of the present invention provides a method for matching floor plans with corresponding renderings. Based on the above embodiment 1, before step S100, which involves obtaining a 2D floor plan and converting each independent spatial area in the 2D floor plan into corresponding floor plan vector data, the method further includes:

[0081] Step S500: Obtain the effect image from the feature library, perform semantic segmentation on the effect image, and convert the effect image into a corresponding effect vector image;

[0082] As mentioned above, semantic segmentation is an image classification and localization method based on deep learning. Existing technologies include instance segmentation and semantic segmentation. Semantic segmentation classifies images at the pixel level; pixels belonging to the same category are grouped together. Therefore, semantic segmentation understands images at the pixel level. For example, in an image, pixels belonging to people are grouped into one category, pixels belonging to motorcycles are grouped into another, and background pixels are also grouped into a separate category. Semantic segmentation differs from instance segmentation. For instance, if a photo contains multiple people, semantic segmentation simply groups all the pixels of people into one category, but instance segmentation further separates the pixels of different people into different categories. In other words, instance segmentation goes a step further than semantic segmentation.

[0083] This embodiment uses semantic segmentation, which can distinguish and label different individuals and elements in the graph.

[0084] The effect vector diagram is vector data corresponding to the effect diagram. The data includes a set of data with structural and shape features extracted from the effect diagram.

[0085] In the effect vector data, feature data such as door position, door size, window position, window size, furniture shape and size, and the like can be included.

[0086] In step S600, based on the segmentation result of the speech segmentation, the feature index diagram is constructed according to the effect vector diagram, the correspondence between the feature index diagram and the effect diagram is established, and the feature index diagram is stored in the feature library.

[0087] The feature index diagram is an index diagram for retrieval with features of part or all elements in the effect diagram corresponding to the effect diagram.

[0088] After the effect diagram is vectorized, the feature index diagram is obtained in 2D plane and vectorization by combining the features in the effect vector diagram obtained before, and the feature index diagram is stored in the feature library.

[0089] Each feature index diagram has a corresponding effect diagram, and the two have a corresponding relationship.

[0090] A large number of effect diagrams can be pre-stored in the feature library, and a corresponding feature index diagram is constructed according to the algorithm in the embodiment for further retrieval in the feature library.

[0091] Further, referring to Figure 5 , the step S500 of performing semantic segmentation on the effect diagram and converting the effect diagram into a corresponding effect vector diagram includes:

[0092] In step S510, the element feature information in the effect diagram is extracted as the segmentation result based on the semantic segmentation algorithm using the trained recognition model.

[0093] The recognition model is pre-trained by a large number of effect diagrams, and according to the semantic segmentation algorithm, the element feature information in each effect diagram can be extracted.

[0094] The element feature information includes the number of doors, the position of the door, the size of the door, the number of windows, the size of the window, the position of the window, and the like. In addition, other elements such as the size, position, and number of furniture, specific items, and the like can also be included.

[0095] In this embodiment, through the semantic segmentation algorithm, the element feature information of the corresponding elements in the effect diagram can be located and obtained by the recognition model, such as the number of doors, the number of windows, and the relative or absolute position (coordinates), etc.

[0096] Step S520, fitting the effect picture into a corresponding effect vector picture.

[0097] The effect picture is fitted, and thus the effect vector picture can be obtained.

[0098] The effect vector picture is vector data including element feature information and constructed according to the positions and relative relationships of each unit or component in the effect picture. The vector data can be in the form of a vector picture. For example, the walls and furniture in the effect picture are abstracted from the original effect picture in a line manner to form a three-dimensional line picture.

[0099] The effect picture is abstracted into vector data and a vector picture, so that the effect picture and the vector picture can be associated on the premise of preserving the position relationship and element features. Further retrieval is facilitated, and the color, texture and other features that interfere with the image similarity and matching degree calculation in the original picture can be removed, so that the further matching process is more accurate and efficient.

[0100] Further, with reference to Figure 6 , the step S520 of fitting the effect picture into a corresponding effect vector picture comprises:

[0101] Step S521, extracting pixel vector data of the effect picture.

[0102] The pixel vector data does not include element feature information, but is simply image data constructed by the original effect picture. The pixel vector data is simply the 3D overall house structure in the original effect picture.

[0103] Step S522, fitting the effect picture into a top-view angle effect vector picture according to the pixel vector data and the segmentation result.

[0104] The pixel vector data is combined with the segmentation result containing element feature information obtained by semantic segmentation, so as to construct the effect vector picture.

[0105] In the method of the embodiment, a three-dimensional point line picture representing the features of the overall house structure is obtained, and the features of the positions and sizes of the doors and windows obtained by semantic segmentation are combined to construct a top-view angle vector data, which can be represented in the form of a vector picture.

[0106] Further, with reference to Figure 7 , the step S521 of extracting the pixel vector data of the effect picture comprises:

[0107] Step S5211, extracting the wall corner point feature in the effect picture;

[0108] The wall corner point feature is the intersection of the connection of the lines of the wall surface. In the effect picture, there are different endpoints of the intersection between the three-dimensional wall surface and the wall surface. The wall corner point feature is the relative position and relationship of the wall surface in the effect picture.

[0109] Step S5212, according to the wall corner point feature, obtaining the number of walls, the distance relationship of walls, and the adjacent relationship of walls in the effect picture, and taking the number of walls, the distance relationship of walls, and the adjacent relationship of walls as the pixel vector data.

[0110] The wall corner point feature of the effect picture can obtain the number of walls, the distance relationship of walls, and the adjacent relationship of walls, and the above parameters can be pixel vector data.

[0111] In addition, with reference to Figure 8 The application also provides a matching device for a 2D house type picture corresponding to an effect picture, comprising:

[0112] An acquisition module 10 is configured to acquire a 2D house type picture and convert each independent space region in the 2D house type picture into corresponding house type vector data;

[0113] An extraction module 20 is configured to extract house feature information in the house type vector data and construct a corresponding feature sample picture based on the house feature information;

[0114] A comparison module is configured to compare the feature sample picture with a feature index picture in a preset feature library;

[0115] The extraction module 20 is further configured to extract the feature index picture with the highest matching degree and acquire an effect picture corresponding to the feature index picture as a matching result corresponding to the independent space region in the 2D house type picture.

[0116] In addition, the application also provides a matching system for a 2D house type picture corresponding to an effect picture, comprising a memory and a processor. The memory is configured to store a matching program for a 2D house type picture corresponding to an effect picture, and the processor is configured to run the matching program for a 2D house type picture corresponding to an effect picture to enable the matching system for a 2D house type picture corresponding to an effect picture to perform the matching method for a house type picture corresponding to an effect picture.

[0117] In addition, the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a matching program for a 2D house type picture corresponding to an effect picture. When the matching program for a 2D house type picture corresponding to an effect picture is executed by a processor, the matching method for a house type picture corresponding to an effect picture is realized.

[0118] In summary, the application provides a matching method, device and system of house type drawing corresponding effect drawing and storage medium. The method converts the acquired 2D house type drawing into house type vector data, extracts house feature information and constructs a feature sample drawing, and then matches the feature sample drawing with feature index drawings in a feature library, selects an effect drawing corresponding to a feature index drawing with the highest matching degree, realizes matching association and retrieval between the 2D house type drawing and the effect drawing, makes the 2D house type drawing and the effect drawing be associated with bridge data according to the human brain thought, avoids the defect of manual searching and finding one by one, improves the matching and searching efficiency and accuracy, and provides support for pushing services, data statistics, garbage data elimination and the like.

[0119] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0120] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and a general hardware platform, and of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on this understanding, the technical solutions of the application can be embodied in the form of a software product, which is stored in a storage medium such as a ROM / RAM, a magnetic disc or an optical disc, and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server or a network device) execute the method described in each embodiment of the application. The above is only a preferred embodiment of the application, and does not limit the patent scope of the application. Any equivalent structure or equivalent flow transformation obtained by using the content of the specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the application.

Claims

1. A method for matching floor plans with renderings, characterized in that, include: Obtain the effect image from the feature library, perform semantic segmentation on the effect image, and convert the effect image into a corresponding effect vector image; Based on the segmentation results of speech segmentation, a feature index map is constructed according to the effect vector map, and the correspondence between the feature index map and the effect map is established and the feature index map is stored in the feature library. Obtain a 2D floor plan and convert each independent spatial area in the 2D floor plan into corresponding floor plan vector data; The spatial features and floor plan features are obtained from the house feature information of the floor plan vector data; the spatial features include wall thickness, wall angle, wall size and proportion; the floor plan features include window position, window features, door direction and door position. Based on the spatial features and the apartment layout features, construct a feature sample map corresponding to the apartment layout vector data; The feature sample image is compared with the feature index image in the preset feature library; Extract the feature index map with the highest matching degree and obtain the effect map corresponding to the feature index map as the matching result corresponding to the independent spatial area in the 2D floor plan.

2. The method for matching floor plans with renderings as described in claim 1, characterized in that, The step of semantically segmenting the effect image and converting it into a corresponding effect vector image includes: Using a trained recognition model and a semantic segmentation algorithm, the element feature information in the resulting image is extracted as the segmentation result. The resulting image is fitted into a corresponding vector graphic.

3. The method for matching floor plans with renderings as described in claim 2, characterized in that, The step of fitting the effect image into a corresponding effect vector image includes: Extract the pixel vector data of the resulting image; Based on the pixel vector data and the segmentation results, the effect image is fitted into the effect vector image from a top-down perspective.

4. The method for matching floor plans with renderings as described in claim 3, characterized in that, The extraction of pixel vector data from the rendered image includes: Extract the corner features from the rendered image; Based on the corner point features, the number of walls, their distance relationship, and their adjacency relationship in the rendering are obtained, and the number of walls, their distance relationship, and their adjacency relationship are used as the pixel vector data.

5. A matching device for 2D floor plans and corresponding renderings, characterized in that, include: The acquisition module is used to acquire a 2D floor plan and convert each independent spatial area in the 2D floor plan into corresponding floor plan vector data. Before this, the module also includes: acquiring renderings from a feature library, performing semantic segmentation on the renderings, and converting the renderings into corresponding rendering vector images; based on the segmentation results of speech segmentation, constructing a feature index map according to the rendering vector images, establishing a correspondence between the feature index map and the renderings, and storing the feature index map in the feature library. An extraction module is used to obtain spatial features and floor plan features from the house feature information of the floor plan vector data; the spatial features include wall thickness, wall angle, wall size and proportion; the floor plan features include window position, window features, door direction and door position; based on the spatial features and the floor plan features, a feature sample map corresponding to the floor plan vector data is constructed; The comparison module is used to compare the feature sample image with the feature index image in the preset feature library; The extraction module is further configured to extract the feature index map with the highest matching degree and obtain the effect map corresponding to the feature index map as the matching result corresponding to the independent spatial area in the 2D floor plan.

6. A matching system for 2D floor plans and corresponding renderings, characterized in that, The system includes a memory and a processor. The memory is used to store a matching program for 2D floor plans and corresponding renderings. The processor runs the matching program for 2D floor plans and corresponding renderings to enable the matching system for 2D floor plans and corresponding renderings to perform the matching method for floor plans and corresponding renderings as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a matching program for 2D floor plan and corresponding rendering, and when the matching program is executed by a processor, it implements the matching method for floor plan and corresponding rendering as described in any one of claims 1-4.

Images