Interior design drawing system and method

Abstract

The invention provides an interior design drawing system and method, and the method comprises the steps: carrying out the image feature mapping of an indoor filling drawing, obtaining a plurality of filling degree recognition boundaries, carrying out the boundary filling degree recognition based on boundary texture features, and obtaining a drawing filling degree corresponding to the indoor filling drawing; obtaining an image center point of the indoor filling drawing, extracting an image filling feature vector corresponding to each filling degree identification boundary, and correcting the image center point according to the image filling feature vector corresponding to each filling degree identification boundary to obtain a filling center point of the indoor filling drawing; according to the stretching coefficient vector and the filling center point, the indoor filling drawing is subjected to radial stretching, and an indoor design drawing is obtained. Therefore, the image focusing area is dynamically changed according to the filling content in the process of carrying out structure filling on the indoor drawing, and the authenticity of the indoor design drawing is improved.

Description

Technical Field

[0001] The present application relates to the technical field of drawing design, and more particularly, to an interior design drawing system and method. Background Art

[0002] Interior design drawing refers to the techniques and processes used to graphically express the design intent, layout, and decorative effects of an interior space. It is a crucial component of interior design, transforming a designer's creative ideas into visual drawings or models. It serves as a bridge between interior design creativity and reality, transforming design concepts into actionable solutions through graphical means.

[0003] Existing interior design drawing concepts usually require the interior space to be structurally filled based on user ideas. However, during the process of continuous structural filling, due to the fixed perspective and space of the interior space, static images and models cannot show the actual use effect of the space. It is difficult for customers to intuitively feel the dynamic changes of the space, which reduces the credibility and realism of the space design. Summary of the Invention

[0004] The present application provides an interior design drawing system and method, which can radially stretch an interior filling drawing based on the drawing filling degree and the filling center point, thereby dynamically changing the image focus area according to the filling content during the process of structural filling of the interior drawing, thereby improving the authenticity of the interior design drawing.

[0005] In a first aspect, the present application provides an interior design drawing method, which can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes: Receiving preset interior furniture element parameters, and performing design filling on the initial interior drawing based on the user design instruction and the interior furniture element parameters to obtain an interior filling drawing; Performing image feature mapping on the indoor infill drawing to obtain a plurality of filling degree identification boundaries, extracting boundary texture features of the filling degree identification boundaries, performing boundary filling degree identification based on the boundary texture features, and obtaining a drawing filling degree corresponding to the indoor infill drawing; Obtaining the center point of the indoor filling drawing image, extracting the image filling feature vectors corresponding to each filling degree identification boundary, and correcting the image center point according to the image filling feature vectors corresponding to each filling degree identification boundary to obtain the filling center point of the indoor filling drawing; Initial stretching parameters are obtained, a stretching coefficient vector is determined based on the drawing filling degree and the initial stretching parameters, and the interior filling drawing is radially stretched according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

[0007] In conjunction with the first aspect, in certain implementations of the first aspect, generating an initial indoor map based on the laser scanning point cloud information specifically includes: Segmenting the point cloud data into different point cloud data groups according to the distribution of point cloud data in the laser scanning point cloud information, performing feature learning on the point cloud data groups, and determining feature labels corresponding to the different point cloud data groups; Based on different point cloud data feature labels, the point cloud data group corresponding to the indoor wall labels is extracted for three-dimensional plane mapping to generate the initial indoor drawing.

[0008] In conjunction with the first aspect, in certain implementations of the first aspect, performing image feature mapping on the indoor filling drawing to obtain multiple filling degree recognition boundaries specifically includes: Obtain laser scanning point cloud information of the target indoor space; Extracting three-dimensional scanning inflection points and their corresponding link tags based on the laser scanning point cloud information, and mapping image feature points of the indoor filling drawing based on the three-dimensional scanning inflection points to obtain a plurality of image feature points in the indoor filling drawing; According to each 3D scanning inflection point and the corresponding link label, the link pixel points between the image feature points are extracted to form the filling degree identification boundary.

[0009] In conjunction with the first aspect, in certain implementations of the first aspect, extracting boundary texture features of the fill-degree identification boundary, performing boundary fill-degree identification based on the boundary texture features, and obtaining the drawing fill-degree corresponding to the indoor fill drawing specifically includes: Obtaining a preset texture recognition depth, and extracting link pixel points for each fill recognition boundary based on the texture recognition depth; For any fill-degree identification boundary, obtain the boundary separation direction, calculate the neighborhood pixel gradient of each link pixel point of the fill-degree identification boundary based on the boundary separation direction, select the link pixel points whose neighborhood pixel gradient is lower than a preset threshold as the fill pixel points, and determine the boundary fill degree corresponding to the fill-degree identification boundary based on the proportion of the fill pixel points; Based on the boundary filling degrees corresponding to the respective filling degree identification boundaries, a drawing filling degree corresponding to the indoor filling drawing is determined.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, extracting the image filling feature vector corresponding to each filling degree identification boundary specifically includes: Obtain each filling degree identification boundary and its corresponding filling pixel points; For any filling pixel point, determine the feature subvector corresponding to the filling pixel point based on the neighborhood pixel gradient and spatial position of the filling pixel point; For any filling degree recognition boundary, the corresponding image filling feature vector is determined based on the feature subvectors of each filling pixel point in the filling degree recognition boundary.

[0011] In combination with the first aspect, in some implementations of the first aspect, before receiving the preset indoor furniture element parameters, the method further includes: collecting indoor laser scanning point cloud information in the corresponding target indoor space, and generating an initial indoor drawing based on the laser scanning point cloud information.

[0012] In combination with the first aspect, in certain implementations of the first aspect, a laser scanning device is used to scan the indoor environment of the target indoor space to obtain the laser scanning point cloud information.

[0013] In a second aspect, the present application provides an interior design drawing system, which includes a drawing control unit, wherein the drawing control unit includes: An image filling module is configured to receive preset indoor furniture element parameters and perform design filling on the initial indoor drawing based on a user design instruction and the indoor furniture element parameters to obtain an indoor filled drawing; a drawing processing module configured to perform image feature mapping on the indoor infill drawing to obtain a plurality of fill-degree identification boundaries, extract boundary texture features of the fill-degree identification boundaries, perform boundary fill-degree identification based on the boundary texture features, and obtain a drawing fill-degree corresponding to the indoor infill drawing; The drawing processing module is further configured to obtain a center point of the indoor filling drawing image, extract image filling feature vectors corresponding to each filling degree identification boundary, and correct the image center point according to the image filling feature vectors corresponding to each filling degree identification boundary to obtain a filling center point of the indoor filling drawing; The drawing processing module is further configured to obtain initial stretching parameters, determine a stretching coefficient vector based on the drawing filling degree and the initial stretching parameters, and radially stretch the interior filling drawing according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

[0014] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned interior design drawing method.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the operations performed by the above-mentioned interior design drawing method.

[0016] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The present application provides an interior design drawing system and method, which first receives preset interior furniture element parameters, performs design filling on an initial interior drawing based on user design instructions and the interior furniture element parameters, and obtains an interior fill drawing; performs image feature mapping on the interior fill drawing to obtain multiple fill degree identification boundaries, extracts boundary texture features of the fill degree identification boundaries, performs boundary fill degree identification based on the boundary texture features, and obtains the drawing fill degree corresponding to the interior fill drawing; obtains the center point of the interior fill drawing image, extracts the image filling feature vectors corresponding to each fill degree identification boundary, corrects the image center point according to the image filling feature vectors corresponding to each fill degree identification boundary, and obtains the filling center point of the interior fill drawing; obtains initial stretching parameters, determines a stretching coefficient vector based on the drawing fill degree and the initial stretching parameters, and radially stretches the interior fill drawing according to the stretching coefficient vector and the filling center point to obtain the interior design drawing.

[0017] It can be seen that the present application analyzes the texture characteristics and spatial distribution of the filling area through the drawing filling degree, quantifies the filling degree of furniture and decorations in the interior space, and provides data support for the dynamic adjustment of the focus area; obtains the filling center point by correcting the center point of the image, and reflects the distribution center of gravity of the filling content in the interior space through the filling center point, so as to dynamically identify areas with higher filling density and stretch them, thereby optimizing the spatial layout, and determines the stretching coefficient vector based on the drawing filling degree and the initial stretching parameter, thereby determining the stretching strength of the focus area, thereby balancing the detail display of the focus area and improving the overall coordination of the image. Through the dynamic adjustment of the drawing filling degree and the filling center point, the system can dynamically identify and focus on key areas in the design, making the design drawing more in line with actual use needs and enhancing the sense of reality.

[0018] In summary, the present application can radially stretch the interior filling drawing based on the drawing filling degree and filling center point, thereby dynamically changing the image focus area according to the filling content during the process of structural filling of the interior drawing, thereby improving the authenticity of the interior design drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is an exemplary flow chart of an interior design drawing method according to some embodiments of the present application; Figure 2is a schematic structural diagram of a graphics control unit according to some embodiments of the present application; Figure 3 It is a structural diagram of a computer terminal device for implementing an interior design drawing method according to some embodiments of the present application. DETAILED DESCRIPTION

[0020] The present application receives preset interior furniture element parameters, and based on user design instructions and interior furniture element parameters, performs design filling on an initial interior drawing to obtain an interior filling drawing; performs image feature mapping on the interior filling drawing to obtain multiple filling degree recognition boundaries, extracts boundary texture features of the filling degree recognition boundaries, performs boundary filling degree recognition based on the boundary texture features, and obtains the drawing filling degree corresponding to the interior filling drawing; obtains the center point of the interior filling drawing image, extracts the image filling feature vectors corresponding to each filling degree recognition boundary, corrects the image center point according to the image filling feature vectors corresponding to each filling degree recognition boundary, and obtains the filling center point of the interior filling drawing; obtains initial stretching parameters, determines a stretching coefficient vector based on the drawing filling degree and the initial stretching parameters, radially stretches the interior filling drawing according to the stretching coefficient vector and the filling center point to obtain an interior design drawing, and can radially stretch the interior filling drawing based on the drawing filling degree and the filling center point, thereby dynamically changing the image focus area according to the filling content during the process of structural filling of the interior drawing, thereby improving the authenticity of the interior design drawing.

[0021] In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 , which is an exemplary flow chart of an interior design drawing method according to some embodiments of the present application. The interior design drawing method 100 mainly includes the following steps: In step S101, preset indoor furniture element parameters are received, and based on user design instructions and the indoor furniture element parameters, an initial indoor drawing is designed and filled to obtain an indoor filled drawing.

[0022] Optionally, in some embodiments, before receiving the preset indoor furniture element parameters, the method further includes: collecting indoor laser scanning point cloud information in the corresponding target indoor space, and generating an initial indoor drawing based on the laser scanning point cloud information.

[0023] Optionally, in some embodiments, a LiDAR laser scanning device can be used to scan the indoor environment to obtain the laser scanning point cloud information, wherein the laser scanning point cloud information is planar two-dimensional coordinate information. In specific implementation, the laser scanning device is placed at multiple preset ground points indoors for laser scanning and acquisition. The laser scanning device calculates the distance between the indoor wall and the laser scanning device by measuring the time from the laser being emitted to the time it is reflected back to the device. Through multiple scans, dense three-dimensional point cloud data is generated, and each point contains three-dimensional coordinate information.

[0024] Preferably, in some embodiments, generating an initial indoor map based on the laser scanning point cloud information specifically includes: Segmenting the laser scanning point cloud information into different point cloud data groups according to the distribution of point cloud data in the laser scanning point cloud information, performing feature learning on the point cloud data groups, and determining feature labels corresponding to the different point cloud data groups; Based on different point cloud data feature labels, the point cloud data group corresponding to the indoor wall labels is extracted for three-dimensional plane mapping to generate the initial indoor drawing.

[0025] In a specific implementation, each data point in the laser scanning point cloud information contains corresponding three-dimensional coordinate information. The K-Means clustering algorithm is used to cluster and learn features of the point cloud. Each point cloud data group represents a spatial structure (such as a wall, furniture, etc.), and feature labels are performed based on the spatial structure. In some embodiments, the wall structure can be identified by the normal vector of the point cloud and the plane fitting algorithm, and the extracted wall point cloud data can be plane fitted to generate a three-dimensional wall model, and then the three-dimensional wall model can be visualized using a three-dimensional modeling tool to obtain the initial indoor drawing.

[0026] It should be noted that the indoor furniture element parameters include the geometric size parameters, shape information parameters, placement rule parameters, texture color parameters, etc. corresponding to each indoor furniture, such as a sofa, table, and bed. In specific implementation, the indoor furniture element parameters can be calibrated as constants based on historical experience, or they can be obtained by collecting parameters of actual furniture targets. This application does not limit this.

[0027] Optionally, in some embodiments, performing design filling on the initial interior drawing based on the user design instruction and the interior furniture element parameters to obtain the interior filling drawing specifically includes: Selecting a corresponding furniture element according to the user design instruction, and obtaining a geometric shape and texture corresponding to the furniture element from the indoor furniture element parameters; The geometric shapes of the various furniture elements are drawn into the plan view, the texture and color of the various furniture elements are obtained, and the appearance of the furniture elements is filled to obtain an interior filling drawing.

[0028] In step S102, image feature mapping is performed on the indoor filling drawing to obtain a plurality of filling degree recognition boundaries, boundary texture features of the filling degree recognition boundaries are extracted, and boundary filling degree recognition is performed based on the boundary texture features to obtain the drawing filling degree corresponding to the indoor filling drawing.

[0029] It should be noted that the fill-degree identification boundary is a boundary line segment of the wall background in the indoor fill drawing. The fill-degree identification boundary is used to identify the image fill degree and fill position in the indoor fill drawing. Optionally, in some embodiments, performing image feature mapping on the indoor fill drawing to obtain multiple fill-degree identification boundaries specifically includes: Obtain laser scanning point cloud information of the target indoor space; Extracting three-dimensional scanning inflection points and their corresponding link tags based on the laser scanning point cloud information, and mapping image feature points of the indoor filling drawing based on the three-dimensional scanning inflection points to obtain a plurality of image feature points in the indoor filling drawing; According to each 3D scanning inflection point and the corresponding link label, the link pixel points between the image feature points are extracted to form the filling degree identification boundary.

[0030] It should be noted that the three-dimensional scanning inflection point is a point with a large curvature change in the laser scanning point cloud information. It is located at the edge of the wall structure and can be used to identify the background area boundary of the wall background. The three-dimensional scanning inflection points have a link relationship. After using the corresponding recognition algorithm to identify the link relationship between each three-dimensional scanning inflection point, each three-dimensional scanning inflection point and the corresponding link label are obtained. For example, if there is only one dimensional coordinate difference between two three-dimensional scanning inflection points, it can be identified that there is a link relationship between the two three-dimensional scanning inflection points. In specific implementation, the link label can be in the form of a vector. For example, the three-dimensional scanning inflection points are sorted, and the vector length is the number of three-dimensional scanning inflection points. For three-dimensional scanning inflection points with a link relationship, the vector element is set to 1 at the corresponding position, and for three-dimensional scanning inflection points without a link relationship, the vector element is set to 0 at the corresponding position. This application does not elaborate on this.

[0031] In a specific implementation, the three-dimensional scanning inflection point is mapped to the indoor filling drawing for image feature points. In the process of obtaining multiple image feature points in the indoor filling drawing, the coordinates of the three-dimensional scanning inflection point are matched with the indoor filling drawing for pixel points, and a nearest neighbor search algorithm is used to find the point closest to the inflection point in the three-dimensional image as the image feature point. The image feature point is used to represent the key position of the indoor wall structure, such as the wall corner. Then, according to the link label of the three-dimensional inflection point, the three-dimensional image feature points are connected into links, each link representing a filling degree recognition boundary. After each link is interpolated, all points on the link are extracted to form a filling degree recognition boundary.

[0032] It should be noted that the drawing fillness indicates a summary of the furniture filling design process for the interior drawing. The drawing fillness is used to analyze the texture characteristics and spatial distribution of the filled area, thereby quantifying the filling degree of furniture and decorations in the interior space, reflecting the filling density and distribution of different areas, and providing data support for dynamically adjusting the focus area. Optionally, in some embodiments, boundary texture features of the filling degree identification boundary are extracted, and boundary filling degree identification is performed based on the boundary texture features to obtain the drawing fillness corresponding to the interior filled drawing. Specifically, the following steps are performed: Obtaining a preset texture recognition depth, and extracting link pixel points for each fill recognition boundary based on the texture recognition depth; For any fill-degree identification boundary, obtain the boundary separation direction, calculate the neighborhood pixel gradient of each link pixel point of the fill-degree identification boundary based on the boundary separation direction, select the link pixel points whose neighborhood pixel gradient is lower than a preset threshold as the fill pixel points, and determine the boundary fill degree corresponding to the fill-degree identification boundary based on the proportion of the fill pixel points; Based on the boundary filling degrees corresponding to the respective filling degree identification boundaries, a drawing filling degree corresponding to the indoor filling drawing is determined.

[0033] In a specific implementation, in the process of extracting link pixel points for each filling degree identification boundary based on the texture recognition depth, the texture recognition depth represents the number of samples for equally spaced sampling of link pixel points for a single filling degree identification boundary; wherein the boundary separation direction is the area separation direction on both sides of the filling degree identification boundary. In some embodiments, the vertical direction of the filling degree identification boundary can be used as the boundary separation direction corresponding to the filling degree identification boundary; wherein, in the process of performing neighborhood texture feature screening on each link pixel point of the filling degree identification boundary based on the boundary separation direction and using the screened link pixel points as filling pixel points, neighborhood pixel gradient calculation can be performed on each link pixel point of the filling degree identification boundary based on the boundary separation direction, that is, obtaining pixel points in the neighborhood range of the link pixel point, extracting the grayscale gradient in the boundary separation direction as the neighborhood pixel gradient based on the pixel points in the neighborhood range, and then using the link pixel points whose absolute value of the neighborhood pixel gradient is lower than the preset gradient threshold as the filling pixel point.

[0034] Optionally, in some embodiments, the ratio between the number of all link pixels and the number of screened filling pixels in the filling degree identification boundary can be used as the boundary filling degree corresponding to the filling degree identification boundary, and the average of the boundary filling degrees corresponding to all filling degree identification boundaries can be used as the drawing filling degree corresponding to the indoor filling drawing. This application does not elaborate on this.

[0035] In step S103, the image center point of the indoor filling drawing is obtained, the image filling feature vectors corresponding to each filling degree identification boundary are extracted, and the image center point is corrected according to the image filling feature vectors corresponding to each filling degree identification boundary to obtain the filling center point of the indoor filling drawing.

[0036] Optionally, in some embodiments, the image coordinate center point of the indoor fill drawing is used as the image center point of the indoor fill drawing.

[0037] It should be noted that the image filling feature vector represents an offset feature vector of the filling center relative to the image center point during the process of filling the interior space with furniture design. Optionally, in some embodiments, extracting the image filling feature vector corresponding to each filling degree identification boundary specifically includes: Obtain each filling degree identification boundary and its corresponding filling pixel points; For any filling pixel point, determine the feature subvector corresponding to the filling pixel point based on the neighborhood pixel gradient and spatial position of the filling pixel point; For any filling degree recognition boundary, the corresponding image filling feature vector is determined based on the feature subvectors of each filling pixel point in the filling degree recognition boundary.

[0038] In a specific implementation, in the feature sub-vector corresponding to the filling pixel point, the vector length of the feature sub-vector is the neighborhood pixel gradient corresponding to the filling pixel point, and the vector direction of the feature sub-vector is the pointing direction of the image center point to the filling pixel point. In a specific implementation, the feature sub-vectors of each filling pixel point in the filling degree identification boundary can be vector-averaged weighted to obtain the image filling feature vector corresponding to the filling degree identification boundary.

[0039] It should be noted that the filling center point is obtained by correcting the image center point. The filling center point reflects the distribution center of the filling content in the indoor space, that is, it represents the filling center position in the process of filling the indoor space with furniture design. Based on the filling center point, the system can determine the area that needs to be focused on, ensuring that the key areas of the design drawing are highlighted. The interior design drawing is radially stretched based on the filling center point, which can actually correct the radial distortion of the camera during the image acquisition process, thereby improving the focus of the filling center area. At the same time, it can avoid the sense of space crowding caused by the transition of furniture filling, enhance the sense of indoor space, and improve the authenticity of the interior design drawing. Optionally, in some embodiments, the image center point is corrected according to the image filling feature vector corresponding to each filling degree recognition boundary, and the filling center point of the indoor filling drawing is obtained specifically including: Performing vector superposition on the image filling feature vectors corresponding to the respective filling degree recognition boundaries to obtain a filling center correction vector, and performing feature normalization on the image filling feature vector based on a preset unit vector length to obtain a center correction direction and a center correction distance; The center point of the image is corrected according to the center correction direction and the center correction distance to obtain the filling center point of the indoor filling drawing.

[0040] In specific implementation, the image center point can be pixel-shifted based on the center correction direction and the center correction distance to obtain the coordinate position corresponding to the filling center point, and then the image pixel point corresponding to the coordinate position is used as the filling center point.

[0041] In step S104, initial stretching parameters are obtained, a stretching coefficient vector is determined based on the drawing filling degree and the initial stretching parameters, and the interior filling drawing is radially stretched according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

[0042] Optionally, in some embodiments, obtaining the initial stretching parameter specifically includes: capturing a panoramic image of the target indoor space using a panoramic camera, wherein the panoramic image contains a plurality of distortion marker points; Determining the distorted coordinates of a plurality of distorted marker points in the indoor image, and obtaining the coordinates of corresponding comparison marker points in the initial indoor drawing for coordinate comparison, to obtain offset coordinates corresponding to the plurality of distorted marker points; The center distances corresponding to the respective distortion markers are obtained, and the offset coordinates are fitted based on the center distances corresponding to the respective distortion markers to obtain the initial stretching parameters.

[0043] In a specific implementation, the image distance of each distortion mark point relative to the center position of the panoramic image is used as the center distance. In the process of performing parameter fitting on the offset coordinates based on the center distances corresponding to each distortion mark point, a polynomial parameter model can be constructed according to the center distances and offset coordinates corresponding to the distortion mark points, that is: in, arrive Represent the offset coordinates corresponding to the 1st to nth distortion marker points, respectively. arrive Respectively represent the center distances corresponding to the 1st to nth distortion marker points, where n is the number of distortion marker points. 、 and are the initial stretching parameters to be solved. When the number of distortion landmark points is greater than the number of initial stretching parameters, matrix singular value decomposition can be used to solve the initial stretching parameters in the above homogeneous linear equations. In some other embodiments, the least squares method can also be used to perform parameter fitting on the polynomial parameter model to obtain the initial stretching parameters. This application does not limit this.

[0044] Optionally, in some embodiments, the initial stretching parameters may also be calibrated as a data sequence consisting of constant parameters based on historical experience.

[0045] Preferably, in some embodiments, determining the stretch coefficient vector based on the drawing fillness and the initial stretch parameter specifically includes: obtaining a preset mapping table, mapping the drawing fillness to obtain a corresponding stretch adjustment coefficient based on the mapping table, performing parameter adjustment on the initial stretch parameter using the stretch adjustment coefficient, and filling the coefficient into an empty vector to obtain a stretch coefficient vector. In specific implementation, a threshold area where the drawing fillness is located can be obtained, and the threshold area can be mapped to the corresponding stretch adjustment coefficient using a preset mapping table.

[0046] Preferably, in some embodiments, radially stretching the interior filling drawing according to the stretch coefficient vector and the filling center point to obtain the interior design drawing specifically includes: Determining the filling distances corresponding to the respective pixel points in the indoor filling drawing according to the filling center point; Based on the stretching coefficient vector and the filling distances corresponding to the respective pixel points, the coordinates of the respective pixel points in the interior filling drawing are stretched to obtain the interior design drawing.

[0047] In a specific implementation, the image distance between each pixel point in the indoor filling drawing and the filling center point is used as the filling distance. According to the stretch coefficient vector and the filling distance, the coordinates of each pixel point in the indoor filling drawing are stretched according to the following formula:

[0048] in, is the pixel coordinate after stretching, is the pixel coordinate before stretching, is the stretch coefficient vector, is the filling distance feature vector, r is the filling distance of the pixel point, is the vector dot product symbol.

[0049] Optionally, in some embodiments, the process of obtaining the interior design drawing after coordinate stretching of each pixel point further includes: obtaining the image poles of the interior design drawing, determining a minimum circumscribed matrix based on the image poles, and filling the blank areas within the minimum circumscribed matrix with a solid color.

[0050] In addition, in another aspect of the present application, in some embodiments, the present application provides an interior design drawing system, the system includes a drawing control unit, reference Figure 2 , which is a schematic diagram of the structure of a drawing control unit according to some embodiments of the present application. The drawing control unit 200 includes: an image filling module 201 and a drawing processing module 202, which are described as follows: The image filling module 201 is configured to receive preset indoor furniture element parameters and perform design filling on the initial indoor drawing based on the user design instruction and the indoor furniture element parameters to obtain an indoor filled drawing; A drawing processing module 202 is configured to perform image feature mapping on the indoor infill drawing to obtain a plurality of fill-degree identification boundaries, extract boundary texture features of the fill-degree identification boundaries, perform boundary fill-degree identification based on the boundary texture features, and obtain a drawing fill-degree corresponding to the indoor infill drawing; The drawing processing module 202 is further configured to obtain a center point of the indoor filling drawing image, extract image filling feature vectors corresponding to each filling degree recognition boundary, and correct the image center point according to the image filling feature vectors corresponding to each filling degree recognition boundary to obtain a filling center point of the indoor filling drawing; The drawing processing module 202 is further configured to obtain initial stretching parameters, determine a stretching coefficient vector based on the drawing filling degree and the initial stretching parameters, and radially stretch the interior filling drawing according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

[0051] The above describes in detail an example of an interior design drawing system and method provided by an embodiment of the present application. It can be understood that in order to achieve the above functions, the corresponding device includes a hardware structure and / or software module corresponding to executing each function.

[0052] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, 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.

[0053] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned interior design drawing method.

[0054] In some embodiments, reference Figure 3 , which is a schematic diagram of the structure of a computer terminal device for implementing an interior design drawing method according to some embodiments of the present application. The interior design drawing method in the above embodiment can be Figure 3 The computer terminal device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer terminal device 300 includes at least one communication bus 301 , a communication interface 302 , a processor 303 and a memory 304 .

[0055] The processor 303 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of an interior design drawing method in the present application.

[0056] The communication bus 301 may include a path for transmitting information between the aforementioned components.

[0057] Memory 304 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, an optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 304 may be independent and connected to processor 303 via communication bus 301. Memory 304 may also be integrated with processor 303.

[0058] Memory 304 is used to store program code for executing the solution of the present application, and is controlled by processor 303 for execution. Processor 303 is used to execute the program code stored in memory 304. The program code may include one or more software modules. The determination of the filling center point in the above embodiment can be implemented by processor 303 and one or more software modules in the program code in memory 304.

[0059] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0060] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0061] In a specific implementation, as an example, a computer terminal device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0062] The aforementioned computer terminal device can be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer terminal device.

[0063] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned interior design drawing method.

[0064] In summary, in an interior design drawing system and method disclosed in an embodiment of the present application, first, by receiving preset interior furniture element parameters, based on user design instructions and interior furniture element parameters, an initial interior drawing is designed and filled to obtain an interior filled drawing; image feature mapping is performed on the interior filled drawing to obtain multiple filling degree identification boundaries, boundary texture features of the filling degree identification boundaries are extracted, and boundary filling degree identification is performed based on the boundary texture features to obtain a drawing filling degree corresponding to the interior filled drawing; the center point of the interior filled drawing image is obtained, the image filling feature vector corresponding to each filling degree identification boundary is extracted, and the image center point is corrected according to the image filling feature vector corresponding to each filling degree identification boundary to obtain a filling center point of the interior filled drawing; initial stretching parameters are obtained, a stretching coefficient vector is determined based on the drawing filling degree and the initial stretching parameters, and the interior filled drawing is radially stretched according to the stretching coefficient vector and the filling center point to obtain an interior design drawing. The interior filled drawing can be radially stretched based on the drawing filling degree and the filling center point, so that the image focus area is dynamically changed according to the filling content during the process of structural filling of the interior drawing, thereby improving the authenticity of the interior design drawing.

[0065] The above description is merely an embodiment of the present application. Common knowledge such as the specific technical solutions or features of the solutions is not described in detail herein. It should be noted that those skilled in the art may make various modifications and improvements without departing from the technical solution of the present application, and these modifications and improvements should also be considered within the scope of protection of the present application. These modifications and improvements will not affect the effectiveness of the implementation of the present application or the practical application of the patent.

[0066] The scope of protection claimed by this application shall be determined by the content of the claims. The specific embodiments and other descriptions in the specification may be used to interpret the content of the claims. Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of the invention. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application is intended to include such modifications and variations.

Claims

1. A method for drawing interior design, characterized in that: include: Receiving preset interior furniture element parameters, and performing design filling on the initial interior drawing based on the user design instruction and the interior furniture element parameters to obtain an interior filling drawing; Performing image feature mapping on the indoor infill drawing to obtain a plurality of filling degree identification boundaries, extracting boundary texture features of the filling degree identification boundaries, performing boundary filling degree identification based on the boundary texture features, and obtaining a drawing filling degree corresponding to the indoor infill drawing; Obtaining the center point of the indoor filling drawing image, extracting the image filling feature vectors corresponding to each filling degree identification boundary, and correcting the image center point according to the image filling feature vectors corresponding to each filling degree identification boundary to obtain the filling center point of the indoor filling drawing; Initial stretching parameters are obtained, a stretching coefficient vector is determined based on the drawing filling degree and the initial stretching parameters, and the interior filling drawing is radially stretched according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

2. The method according to claim 1, wherein Performing image feature mapping on the indoor filling drawing to obtain multiple filling degree recognition boundaries specifically includes: Obtain laser scanning point cloud information of the target indoor space; Extracting three-dimensional scanning inflection points and their corresponding link tags based on the laser scanning point cloud information, and mapping image feature points of the indoor filling drawing based on the three-dimensional scanning inflection points to obtain a plurality of image feature points in the indoor filling drawing; According to each 3D scanning inflection point and the corresponding link label, the link pixel points between the image feature points are extracted to form the filling degree identification boundary.

3. The method according to claim 1, wherein Extracting the boundary texture features of the filling degree identification boundary, performing boundary filling degree identification based on the boundary texture features, and obtaining the drawing filling degree corresponding to the indoor filling drawing specifically includes: Obtaining a preset texture recognition depth, and extracting link pixel points for each fill recognition boundary based on the texture recognition depth; For any fill-degree identification boundary, obtain the boundary separation direction, calculate the neighborhood pixel gradient of each link pixel point of the fill-degree identification boundary based on the boundary separation direction, select the link pixel points whose neighborhood pixel gradient is lower than a preset threshold as the fill pixel points, and determine the boundary fill degree corresponding to the fill-degree identification boundary based on the proportion of the fill pixel points; Based on the boundary filling degrees corresponding to the respective filling degree identification boundaries, a drawing filling degree corresponding to the indoor filling drawing is determined.

4. The method according to claim 1, wherein Extracting the image filling feature vector corresponding to each filling degree identification boundary specifically includes: Obtain each filling degree identification boundary and its corresponding filling pixel points; For any filling pixel point, determine the feature subvector corresponding to the filling pixel point based on the neighborhood pixel gradient and spatial position of the filling pixel point; For any filling degree recognition boundary, the corresponding image filling feature vector is determined based on the feature subvectors of each filling pixel point in the filling degree recognition boundary.

5. The method according to claim 1, wherein Before receiving the preset indoor furniture element parameters, the method further includes: collecting indoor laser scanning point cloud information in the corresponding target indoor space, and generating an initial indoor drawing based on the laser scanning point cloud information.

6. The method according to claim 5, wherein Generating an initial indoor map based on the laser scanning point cloud information specifically includes: Segmenting the point cloud data into different point cloud data groups according to the distribution of point cloud data in the laser scanning point cloud information, performing feature learning on the point cloud data groups, and determining feature labels corresponding to the different point cloud data groups; Based on different point cloud data feature labels, the point cloud data group corresponding to the indoor wall labels is extracted for three-dimensional plane mapping to generate the initial indoor drawing.

7. The method according to claim 5, wherein A laser scanning device is used to scan the indoor environment of the target indoor space to obtain the laser scanning point cloud information.

8. An interior design drawing system, comprising a drawing control unit, characterized in that: The drawing control unit includes: An image filling module is configured to receive preset indoor furniture element parameters and perform design filling on the initial indoor drawing based on a user design instruction and the indoor furniture element parameters to obtain an indoor filled drawing; a drawing processing module configured to perform image feature mapping on the indoor infill drawing to obtain a plurality of fill-degree identification boundaries, extract boundary texture features of the fill-degree identification boundaries, perform boundary fill-degree identification based on the boundary texture features, and obtain a drawing fill-degree corresponding to the indoor infill drawing; The drawing processing module is further configured to obtain a center point of the indoor filling drawing image, extract image filling feature vectors corresponding to each filling degree identification boundary, and correct the image center point according to the image filling feature vectors corresponding to each filling degree identification boundary to obtain a filling center point of the indoor filling drawing; The drawing processing module is further configured to obtain initial stretching parameters, determine a stretching coefficient vector based on the drawing filling degree and the initial stretching parameters, and radially stretch the interior filling drawing according to the stretching coefficient vector and the filling center point to obtain an interior design drawing.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the interior design drawing method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the interior design drawing method according to any one of claims 1 to 7.

Images