CN111104704A - Cabinet internal layout design method, device and system and storage medium - Google Patents
Cabinet internal layout design method, device and system and storage medium Download PDFInfo
- Publication number
- CN111104704A CN111104704A CN201911260627.XA CN201911260627A CN111104704A CN 111104704 A CN111104704 A CN 111104704A CN 201911260627 A CN201911260627 A CN 201911260627A CN 111104704 A CN111104704 A CN 111104704A
- Authority
- CN
- China
- Prior art keywords
- cabinet
- functional
- cabinet body
- internal layout
- function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a cabinet body internal layout design method, a device, a system and a storage medium, wherein the method comprises the following steps: obtaining the current internal layout of the cabinet body; designing the class of the functional cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body by using a functional cabinet class determination model constructed according to a deep neural network, and then determining the position of the class of the functional cabinet in the residual space of the cabinet body by using a functional cabinet position determination model constructed according to the deep neural network; when the cabinet body is fully distributed with the functional cabinets, the functional cabinet region segmentation is carried out by utilizing the functional cabinet region segmentation model constructed according to the deep neural network based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets, so that the internal layout design of the cabinet body is realized. The automatic design of the residual space in the cabinet body can be realized based on the current cabinet body internal layout including the cabinet body outline so as to reduce the workload of designers.
Description
Technical Field
The invention belongs to the technical field of furniture design, and particularly relates to a cabinet body internal layout design method, device and system and a storage medium.
Background
In the field of furniture design, especially the design field of the cabinet body, the functional space division and the geometric distribution in the cabinet body have very important significance for the practicability of the cabinet body. Therefore, in designing the cabinet, it is necessary to design a reasonable internal space.
At present, in furniture design, manual operation is required to be performed by a designer in the design of a cabinet body and the layout and division of an internal space, and the specific process is approximately: the method comprises the steps of firstly determining main functions of a cabinet body, then determining functional areas in the cabinet body according to the functions, and finally performing detailed division and design on the sizes of the functional areas, the positions of the functional areas and partition relations. This kind of mode of manual design cabinet body not only needs a large amount of work load of designer to it is consuming time more, and the design effect also highly relies on designer's personal experience accumulation and proficiency simultaneously, can't guarantee the uniformity of design level, and this kind of work intensive simultaneously also can aggravate designer's work burden greatly.
The patent application with application publication number CN108304650A discloses a 3D design method for a cabinet and wardrobe based on a parameter-driven algorithm, which includes adding corresponding object names to components in the wardrobe body, setting expressions of driven components, and driving updating steps.
Patent application with application publication number CN109598017A discloses a method for intelligently generating cabinets based on free wall selection of users, which specifically comprises S1: establishing a scene, entering a cabinet intelligent arrangement mode, and S2: analyzing the number of the walls selected by the user, and when the user finishes selecting the walls and carries out the next arrangement operation, S3: analyzing the kitchen pattern, determining the layout of the kitchen according to the number of the selected walls of the user, S4: adopt expert system matching rule, according to wall body data, the cabinet body that can place of this wall of assay, S5: and (4) converting coordinates, establishing a local coordinate system, and converting the wall information into the local coordinate system, S6: the accurate cabinet body of placing, according to the local coordinator of establishing, S7: and selecting the style by the user and replacing the style. Although the technical scheme can intelligently generate the cabinet, the steps are more and the efficiency is low.
Disclosure of Invention
The embodiment of the invention provides a cabinet internal layout design method, a device, a system and a storage medium, which can realize automatic design of the residual space in the cabinet based on the current cabinet internal layout including the cabinet outline so as to reduce the workload of a designer. The technical scheme is as follows:
in a first aspect, a cabinet interior layout design method includes:
obtaining the current internal layout of the cabinet body;
designing the class of the functional cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body by using a functional cabinet class determination model constructed according to a deep neural network, and then determining the position of the class of the functional cabinet in the residual space of the cabinet body by using a functional cabinet position determination model constructed according to the deep neural network;
when the cabinet body is fully distributed with the functional cabinets, the functional cabinet region segmentation is carried out by utilizing the functional cabinet region segmentation model constructed according to the deep neural network based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets, so that the internal layout design of the cabinet body is realized.
In a second aspect, a cabinet interior layout design apparatus includes:
the acquisition unit is used for acquiring the current internal layout of the cabinet body;
the functional cabinet type determining unit is used for designing the type of the functional cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body by utilizing a functional cabinet type determining model constructed according to the deep neural network;
the functional cabinet position determining unit is used for determining the position of the functional cabinet type in the residual space of the cabinet body by using a functional cabinet position determining model constructed according to the deep neural network;
and the functional cabinet area division module is used for carrying out functional cabinet area division by utilizing a functional cabinet area division model constructed according to the deep neural network based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets.
In a third aspect, a cabinet interior layout design system includes at least one memory, at least one processor, and a computer program stored in the memory and executable on the processor, where the memory stores a functional cabinet type determination model, a functional cabinet position determination model, and a functional cabinet region segmentation model constructed according to a deep neural network, and the processor implements the following steps when executing the computer program:
obtaining the current internal layout of the cabinet body;
calling the function cabinet type determination model to design the type of the function cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body;
calling the function cabinet position determination model to determine the position of the function cabinet type in the residual space of the cabinet body;
when the cabinet body is fully distributed with the function cabinets, the function cabinet region division model is called to carry out function cabinet region division based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the function cabinets, so that the design of the cabinet body internal layout is realized.
In a fourth aspect, a computer-readable storage medium has at least one instruction stored therein, and the at least one instruction is loaded and executed by a processor to implement the operations performed by the cabinet interior layout design method.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the functional cabinet type determination model, the functional cabinet position determination model and the functional cabinet region segmentation model which are constructed according to the deep neural network are used for designing and distributing the functional cabinet in the residual space in the cabinet based on the current internal layout of the cabinet, so that the workload of a designer is reduced, and the internal layout design efficiency of the cabinet is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a cabinet internal layout design method according to an embodiment of the present invention;
fig. 2(a) and fig. 2(b) are schematic diagrams of a current cabinet internal layout in a cabinet internal layout design method according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating determination results of types and positions of functional cabinets in a cabinet internal layout design method according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a result of dividing a functional cabinet region in a cabinet internal layout design method according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a result of optimizing a line rule in the cabinet internal layout design method according to the embodiment of the present invention;
fig. 6 is a schematic structural diagram of a cabinet internal layout design apparatus according to an embodiment of the present invention;
fig. 7(a) -7 (d) are diagrams illustrating the effects of the internal layout design of the cabinet according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
When a cabinet body is designed, a designer firstly considers the actual function application of the cabinet body to determine the required function areas and the approximate distribution positions in the cabinet body, then comprehensively considers the area requirements of different function areas, and reasonably divides the space among the function areas after the convenience degree in use and the overall attractiveness and coordination of the divided function areas are considered.
In order to maximally implement a near-real and fully-automatic cabinet interior layout design, the embodiment of the present invention simulates human thinking, decision and design processes, and provides a flow diagram of a cabinet interior layout design method as shown in fig. 1. Referring to fig. 1, a cabinet with only an outline is taken as an example for designing the internal layout of the cabinet, and the embodiment includes:
and S101, obtaining the current internal layout of the cabinet body.
The current cabinet internal layout may be a cabinet only including a cabinet outline in an initial state, as shown in fig. 2(a), or may be a cabinet internal layout in which a partial functional cabinet together with the cabinet outline has been designed inside the cabinet, as shown in fig. 2 (b). Typically, the current cabinet interior layout appears as a two-dimensional map. Namely, the current internal layout of the cabinet is a two-dimensional color picture, which contains the determined type and position of the functional cabinet within the external contour and/or the external contour of the cabinet, and can be a two-dimensional sectional view or a two-dimensional perspective view. The two-dimensional graph has relatively simple requirements on the network structures of the function cabinet type determination model, the function cabinet position determination model and the function cabinet area division model, the calculation amount can be greatly reduced by adopting the two-dimensional current cabinet body internal layout, the calculation consumption is reduced, and the design efficiency is improved. Of course, the current cabinet interior layout may also present a three-dimensional volumetric structure, regardless of the computational consumption.
S102, designing the functional cabinet type in the residual space of the cabinet body based on the current internal layout of the cabinet body by using a functional cabinet type determination model constructed according to the deep neural network, and determining the position of the functional cabinet type in the residual space of the cabinet body by using a functional cabinet position determination model constructed according to the deep neural network.
The cabinet body may be classified into a wardrobe, a shoe cabinet, a wine cabinet, a common storage cabinet and the like according to functions, that is, the function cabinets include the wardrobe, the shoe cabinet, the wine cabinet, the common storage cabinet and the like, and different function cabinets are combined together according to different combination modes to form different internal layouts of the cabinet body. The combination of the functional cabinets can be regarded as the mutual relationship of a plurality of bounding boxes on the section plane. The process of generating the location and class of the center of each bounding box on the cross-section is similar to the thinking process of the designer in making a preliminary decision about where the functional area of each class is located. Therefore, the embodiment adopts a functional cabinet type determination model and a functional cabinet position determination model which are constructed based on the deep neural network to determine the type and the position of the functional area.
In the embodiment, the function cabinet type determination model and the function cabinet position determination model are both obtained by taking a deep neural network as a network basis and training cabinet data. For example, two Deep neural networks of rest-152 (Deep reactive learning for Image Recognition) can be used as a network basis, the rest-152 is trained by using cabinet data, and network parameters of the rest-152 are optimized to obtain a functional cabinet type determination model and a functional cabinet position determination model.
In the embodiment, cabinet data are sorted, a picture containing a cabinet outline, an existing functional cabinet type and a position is used as an input, a picture containing a next functional cabinet type and a next functional cabinet position is used as an output truth value label, two resnet-152 are supervised and learned, so that the picture-to-figure mapping and the picture-to-picture mapping are learned, network parameters of the two resnet-152 are iteratively optimized, and when the network parameter of the first resnet-152 is determined, a functional cabinet type determination model capable of predicting and outputting the next functional cabinet type according to the input picture is obtained, namely the functional cabinet type determination model can predict and design the functional cabinet type in the residual space of the cabinet according to the input current cabinet internal layout. When the network parameter of the second resnet-152 is determined, a function cabinet position determination model capable of predicting and outputting the position of the next function cabinet according to the input picture is obtained, namely the function cabinet position determination model can predict and design the position corresponding to the type of the function cabinet in the residual space of the cabinet according to the input current cabinet internal layout.
The functional cabinet type determining model outputs a probability array consisting of a group of probability values representing possible functional cabinets, and the functional cabinet corresponding to the maximum probability value is selected from the probability arrays output by the functional cabinet type determining model as the functional cabinet type designed in the residual space of the cabinet body based on the internal layout of the current cabinet body. For example, when the function cabinet type determination model outputs the probability array shown in table 1, a general wardrobe is selected as the function cabinet type of the next predictive design.
TABLE 1
| Common wardrobe | Small drawer | Wardrobe |
| 0.86 | 0.08 | 0.02 |
On the basis of obtaining the function cabinet type determination model and the function cabinet position determination model, the prediction design of the type and the position of the next function cabinet can be performed according to the current cabinet body internal layout, and a schematic diagram of the determination result of the type and the position of the function cabinet is given in fig. 3. Specifically, the preset design process includes: (a) aiming at the internal layout of the cabinet body only comprising the outer contour of the cabinet body, determining whether a first function cabinet and the type of the function cabinet can be put down or not by using a function cabinet type determination model, and if the first function cabinet and the type of the function cabinet can be put down, determining the placing position of the function cabinet of the type of the model by using the position of the function cabinet; (b) based on the current internal layout of the cabinet body including the external contour of the cabinet body and the generated type and position of the function cabinet, determining whether a function cabinet and the type of the function cabinet can be put down by using the function cabinet type determination model, and if the function cabinet can be put down, determining the placing position of the function cabinet of the type of the model by using the position of the function cabinet; (c) and (c) iterating and circularly executing the step (b) until the functional cabinets are fully distributed in the cabinet body.
In the embodiment, the layout condition of the functional cabinets in the cabinet body is judged according to the probability value output by the functional cabinet type determination model and the probability threshold value, and when all the output probability values are smaller than the probability threshold value, the functional cabinets are fully distributed in the cabinet body.
The probability threshold is set according to the type of the functional cabinet and the practical application condition, and when all the output probability values are smaller than the probability threshold, namely, no enough space is available for placing the next functional cabinet in the current environment, the functional cabinet is considered to be fully distributed in the cabinet body.
And S103, when the cabinet body is fully distributed with the functional cabinets, performing functional cabinet region segmentation on the basis of the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets by using a functional cabinet region segmentation model constructed according to the deep neural network so as to realize the internal layout design of the cabinet body.
The functional cabinet area segmentation model is mainly used for generating area division edges, and performing semantic segmentation by taking the edges and the background as two different category labels. The functional cabinet area segmentation model is obtained by taking an area segmentation depth network as a network basis and training cabinet data. For example, google's Mobile-net (Mobile Networks for Mobile Vision Applications) may be used as the depth network for region segmentation, a picture including the cabinet outer contour, each function cabinet type and position is used as an input, a picture including the cabinet outer contour and a detailed edge division is used as an output, and a Mobile-net is used to learn the mapping of the image layer to obtain a function cabinet region segmentation model through iterative optimization, wherein the function cabinet region segmentation model can perform function cabinet region segmentation by the cabinet internal layout.
On the basis of obtaining the functional area division model, the corresponding cabinet body internal layout based on the situation that the cabinet body is fully distributed with the functional cabinets is input into the functional area division model, and the functional area division model is used for carrying out area division on the positions of the functional cabinets in the cabinet body internal layout so as to obtain an area division result, such as a functional cabinet area division result schematic diagram exemplarily shown in fig. 4.
The functional cabinet area segmentation result directly obtained by the functional area segmentation model has correct segmentation lines, but the local part of the functional cabinet area segmentation result is in a hollow shape and directly influences the generation of a subsequent three-dimensional functional cabinet body, so in some embodiments, the cabinet body internal layout design method further includes: and (4) optimizing the line rule of the function cabinet region segmentation result. Namely, the hollow lines in the functional cabinet area segmentation result are subjected to regularization processing to determine the final segmentation line position.
Wherein, the line rule optimization of the segmentation result of the functional cabinet region comprises:
step a, performing mathematical morphology operation on the functional cabinet partition area in sequence, namely performing corrosion expansion operation on the functional cabinet partition area to enable the partition edge to be smoother;
and b, carrying out straight line detection on the operation result of the mathematical morphology, and carrying out direction normalization and merging operation on the detection straight line so as to determine the final region segmentation boundary.
Fig. 5 exemplarily shows a result schematic diagram of performing line rule optimization on the function cabinet region segmentation result, so that the line rule optimization on the function cabinet region segmentation result eliminates a hollow shape locally presented by the segmentation line, and avoids an influence of a hollow shape line on generation of a subsequent three-dimensional function cabinet body.
In some embodiments, the internal layout of the cabinet, which is presented after the functional cabinet position in the residual space of the cabinet is determined by the functional cabinet position determination model, is provided for a user to edit and change the type and position of the functional cabinet in the internal layout of the cabinet.
After the user obtains the internal layout of the cabinet body, the position and the type of the function cabinet can be adjusted according to the preference of the user, or a specific function cabinet and a specific position are added. And then, taking the edited internal layout of the cabinet body as input, and utilizing the functional cabinet type determination model and the functional cabinet position determination model to perform continuous layout of the internal part of the cabinet body, namely continuously designing the type and the corresponding position of the functional cabinet in the residual space of the internal part of the cabinet body.
In some embodiments, the corresponding cabinet internal layout when the cabinet is fully distributed with the functional cabinets is provided for the user, so as to artificially initialize the region partition boundary.
After the obtained internal layout of the cabinet body, a user can draw part of the partition boundaries of the functional cabinet according to the preference of the user, so that the manually initialized region partition boundaries and the internal layout of the cabinet body are input into the region partition model of the functional cabinet, the region partition model of the functional cabinet comprehensively initializes the region partition boundaries to perform region partition of the functional cabinet, and the positions of the boundaries of the remaining functional cabinet are predicted and generated.
According to the cabinet body internal layout design method, the functional cabinet type determination model, the functional cabinet position determination model and the functional cabinet region segmentation model which are constructed according to the deep neural network are used for designing and arranging the functional cabinet in the residual space in the cabinet body based on the current cabinet body internal layout, so that the workload of a designer is reduced, and the cabinet body internal layout design efficiency is greatly improved. In addition, the individuation of the internal layout design of the cabinet is realized by providing the internal layout of the cabinet for users to edit and change the type and the position of the functional cabinet and initialize the division boundary, and the effect diagrams of the internal layout design of part of the cabinet are shown in fig. 7(a) to 7 (d).
Fig. 6 is a schematic structural diagram of a cabinet internal layout design device according to an embodiment of the present invention.
Referring to fig. 6, the embodiment includes:
an obtaining unit 601, configured to obtain a current cabinet internal layout;
a functional cabinet type determining unit 602, configured to design a functional cabinet type in the remaining cabinet space based on the current cabinet internal layout by using a functional cabinet type determination model constructed according to a deep neural network;
a functional cabinet position determining unit 603, configured to determine, by using a functional cabinet position determination model constructed according to a deep neural network, a position of the functional cabinet category in a remaining space of the cabinet body;
the functional cabinet area segmentation module 604 is configured to perform, when the cabinet body is fully populated with functional cabinets, area segmentation on the functional cabinet based on the corresponding cabinet body internal layout when the cabinet body is fully populated with functional cabinets by using a functional cabinet area segmentation model constructed according to the deep neural network.
This internal layout design device of cabinet carries out function cabinet design and overall arrangement to the internal surplus space of cabinet based on the internal overall arrangement of current cabinet through the function cabinet category that founds according to the neural network of degree of depth confirms model, function cabinet position and function cabinet region segmentation model, has reduced designer's work load, has promoted internal layout design efficiency of cabinet greatly.
In some possible embodiments, based on the apparatus composition shown in fig. 6, the apparatus further comprises: and the line optimization unit is used for performing line regularization optimization on the function cabinet region segmentation result.
In some possible embodiments, based on the apparatus composition shown in fig. 6, the apparatus further comprises: and the functional cabinet type and position editing unit is used for providing the internal layout of the cabinet body presented after the functional cabinet position in the residual space of the cabinet body is determined by the functional cabinet position determining model for a user so as to edit and change the type and position of the functional cabinet in the internal layout of the cabinet body.
In some possible embodiments, based on the apparatus composition shown in fig. 6, the apparatus further comprises: and the area division boundary initialization unit is used for providing the corresponding cabinet body internal layout for a user when the cabinet body is fully distributed with the functional cabinets so as to manually initialize the area division boundary.
All the above optional technical solutions can be combined arbitrarily to form the optional embodiments disclosed in the present invention, and are not described herein again.
It should be noted that, when the cabinet internal layout design apparatus provided in the foregoing embodiment performs the cabinet internal layout, the division of the functional units is taken as an example, and the function distribution may be performed by different functional units according to needs, that is, the internal structure of the terminal or the server is divided into different functional units to perform all or part of the functions described above. In addition, the internal layout design device of the cabinet and the internal layout design method provided by the embodiment belong to the same concept, and specific implementation processes of the internal layout design device of the cabinet are detailed in the internal layout design method embodiment of the cabinet, and are not described again.
Embodiments also provide a cabinet interior layout design system, including at least one memory, at least one processor, and a computer program stored in the memory and executable on the processor, where the memory stores a functional cabinet type determination model, a functional cabinet position determination model, and a functional cabinet region segmentation model constructed according to a deep neural network, and the processor implements the following steps when executing the computer program:
obtaining the current internal layout of the cabinet body;
calling the function cabinet type determination model to design the type of the function cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body;
calling the function cabinet position determination model to determine the position of the function cabinet type in the residual space of the cabinet body;
when the cabinet body is fully distributed with the function cabinets, the function cabinet region division model is called to carry out function cabinet region division based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the function cabinets, so that the design of the cabinet body internal layout is realized.
Among other things, the memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory is used to store at least one instruction for execution by a processor to implement a cabinet interior layout design method provided by a method embodiment of the present invention.
According to the internal layout design system of the cabinet, the functional cabinet type determination model, the functional cabinet position determination model and the functional cabinet region segmentation model which are constructed according to the deep neural network are used for designing and distributing the functional cabinet in the residual space in the internal part of the cabinet based on the current internal layout of the cabinet, so that the workload of a designer is reduced, and the internal layout design efficiency of the cabinet is greatly improved.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, including at least one instruction executable by a processor in a terminal to perform the cabinet interior layout design method of the above embodiments is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A cabinet internal layout design method is characterized by comprising the following steps:
obtaining the current internal layout of the cabinet body;
designing the class of the functional cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body by using a functional cabinet class determination model constructed according to a deep neural network, and then determining the position of the class of the functional cabinet in the residual space of the cabinet body by using a functional cabinet position determination model constructed according to the deep neural network;
when the cabinet body is fully distributed with the functional cabinets, the functional cabinet region segmentation is carried out by utilizing the functional cabinet region segmentation model constructed according to the deep neural network based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets, so that the internal layout design of the cabinet body is realized.
2. The cabinet interior layout design method according to claim 1, wherein, from the probability array output by the functional cabinet type determination model, the type of functional cabinet corresponding to the maximum probability value is selected as the functional cabinet type designed in the remaining space of the cabinet based on the current cabinet interior layout.
3. The cabinet internal layout design method according to claim 1, wherein the layout condition of the functional cabinets in the cabinet is judged according to the probability value and the probability threshold value output by the functional cabinet type determination model, and when all the output probability values are smaller than the probability threshold value, the functional cabinets are fully distributed in the cabinet.
4. The cabinet interior layout design method according to any one of claims 1 to 3, further comprising: line rule optimization is carried out on the segmentation result of the functional cabinet area;
wherein the line rule optimization comprises the following steps:
step a: performing mathematical morphology operation on the functional cabinet partition area and performing corrosion expansion operation on the functional cabinet partition area in sequence to enable the partition edge to be smoother;
step b: and performing straight line detection on the mathematical morphology operation result, and performing direction normalization and merging operation on the detected straight lines to determine the final region segmentation boundary.
5. The cabinet interior layout design method of claim 4, further comprising: and the internal layout of the cabinet body presented after the position of the function cabinet in the residual space of the cabinet body is determined by the function cabinet position determining model is provided for a user so as to edit and change the type and the position of the function cabinet in the internal layout of the cabinet body.
6. The cabinet interior layout design method of claim 4 or 5, further comprising: and providing the corresponding internal layout of the cabinet body for a user when the cabinet body is fully distributed with the functional cabinets so as to manually initialize the region division boundary.
7. A cabinet internal layout design device, the device comprising:
the acquisition unit is used for acquiring the current internal layout of the cabinet body;
the functional cabinet type determining unit is used for designing the type of the functional cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body by utilizing a functional cabinet type determining model constructed according to the deep neural network;
the functional cabinet position determining unit is used for determining the position of the functional cabinet type in the residual space of the cabinet body by using a functional cabinet position determining model constructed according to the deep neural network;
and the functional cabinet area division module is used for carrying out functional cabinet area division by utilizing a functional cabinet area division model constructed according to the deep neural network based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the functional cabinets.
8. The cabinet interior layout design apparatus of claim 7, further comprising: the system comprises a line optimization unit, a function cabinet type and position editing unit and a region division boundary initialization unit;
the line optimization unit is used for performing line regularization optimization on the function cabinet region segmentation result;
the functional cabinet type and position editing unit is used for providing the internal layout of the cabinet body presented after the functional cabinet position in the residual space of the cabinet body is determined by the functional cabinet position determining model for a user so as to edit and change the type and position of the functional cabinet in the internal layout of the cabinet body;
the area division boundary initialization unit is used for providing the corresponding cabinet body internal layout for a user when the cabinet body is fully distributed with the functional cabinets so as to manually initialize the area division boundary.
9. A cabinet interior layout design system, comprising at least one memory, at least one processor, and a computer program stored in the memory and executable on the processor, wherein the memory stores a functional cabinet type determination model, a functional cabinet position determination model, and a functional cabinet region segmentation model constructed according to a deep neural network, and the processor executes the computer program to implement the following steps:
obtaining the current internal layout of the cabinet body;
calling the function cabinet type determination model to design the type of the function cabinet in the residual space of the cabinet body based on the current internal layout of the cabinet body;
calling the function cabinet position determination model to determine the position of the function cabinet type in the residual space of the cabinet body;
when the cabinet body is fully distributed with the function cabinets, the function cabinet region division model is called to carry out function cabinet region division based on the corresponding cabinet body internal layout when the cabinet body is fully distributed with the function cabinets, so that the design of the cabinet body internal layout is realized.
10. A computer-readable storage medium, wherein at least one instruction is stored in the storage medium, and is loaded and executed by a processor to implement the operations performed by the cabinet interior layout design method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911260627.XA CN111104704B (en) | 2019-12-10 | 2019-12-10 | Cabinet internal layout design method, device and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911260627.XA CN111104704B (en) | 2019-12-10 | 2019-12-10 | Cabinet internal layout design method, device and system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111104704A true CN111104704A (en) | 2020-05-05 |
| CN111104704B CN111104704B (en) | 2023-08-18 |
Family
ID=70422917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911260627.XA Active CN111104704B (en) | 2019-12-10 | 2019-12-10 | Cabinet internal layout design method, device and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111104704B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112163308A (en) * | 2020-10-13 | 2021-01-01 | 西安理工大学 | Adaptive guide design layout method |
| CN113744350A (en) * | 2021-08-31 | 2021-12-03 | 广州极点三维信息科技有限公司 | Cabinet structure identification method, device, equipment and medium based on single image |
| CN113743009A (en) * | 2021-08-31 | 2021-12-03 | 广州极点三维信息科技有限公司 | Cabinet type intelligent design method, device, equipment and medium based on representation learning |
| CN114722442A (en) * | 2022-06-08 | 2022-07-08 | 广东三维家信息科技有限公司 | Cabinet layout method and device, computer equipment and storage medium |
| CN116070313A (en) * | 2022-12-08 | 2023-05-05 | 广州纬纶信息科技有限公司 | Cabinet intelligent storage layout generation method and device |
| WO2024098051A1 (en) * | 2022-11-04 | 2024-05-10 | Levin Jacqueline M | Methods and systems for space segmentation or organization |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130212513A1 (en) * | 2008-03-11 | 2013-08-15 | Dirtt Environmental Solutions Ltd. | Automatically Creating and Modifying Furniture Layouts in Design Software |
| US20160070824A1 (en) * | 2014-09-05 | 2016-03-10 | Jin Yao | Method for generating design scheme of kitchen |
| CN107122792A (en) * | 2017-03-15 | 2017-09-01 | 山东大学 | Indoor arrangement method of estimation and system based on study prediction |
| CN108304650A (en) * | 2018-01-31 | 2018-07-20 | 广东三维家信息科技有限公司 | A kind of cabinet wardrobe 3D design methods based on driving parameter algorithm |
| CN109033652A (en) * | 2018-08-02 | 2018-12-18 | 江苏艾佳家居用品有限公司 | A kind of indoor autoplacement method based on sliding window feature and regression forecasting |
| CN109117499A (en) * | 2018-07-02 | 2019-01-01 | 东易日盛家居装饰集团股份有限公司 | A kind of cabinet carpentery workshop intelligent distribution method, system and computer equipment |
| CN109598017A (en) * | 2018-10-18 | 2019-04-09 | 广东三维家信息科技有限公司 | A method of freely select wall intelligently to generate cabinet based on user |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
| CN109871604A (en) * | 2019-01-31 | 2019-06-11 | 浙江工商大学 | Indoor function zoning method based on depth confrontation network model |
| CN110096768A (en) * | 2019-04-16 | 2019-08-06 | 江苏艾佳家居用品有限公司 | A kind of method and system fast implementing kitchen autoplacement |
| CN110363853A (en) * | 2019-07-15 | 2019-10-22 | 贝壳技术有限公司 | Furniture puts scheme generation method, device and equipment, storage medium |
| CN110516208A (en) * | 2019-08-12 | 2019-11-29 | 深圳智能思创科技有限公司 | A kind of system and method extracted for PDF document table |
-
2019
- 2019-12-10 CN CN201911260627.XA patent/CN111104704B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130212513A1 (en) * | 2008-03-11 | 2013-08-15 | Dirtt Environmental Solutions Ltd. | Automatically Creating and Modifying Furniture Layouts in Design Software |
| US20160070824A1 (en) * | 2014-09-05 | 2016-03-10 | Jin Yao | Method for generating design scheme of kitchen |
| CN107122792A (en) * | 2017-03-15 | 2017-09-01 | 山东大学 | Indoor arrangement method of estimation and system based on study prediction |
| CN108304650A (en) * | 2018-01-31 | 2018-07-20 | 广东三维家信息科技有限公司 | A kind of cabinet wardrobe 3D design methods based on driving parameter algorithm |
| CN109117499A (en) * | 2018-07-02 | 2019-01-01 | 东易日盛家居装饰集团股份有限公司 | A kind of cabinet carpentery workshop intelligent distribution method, system and computer equipment |
| CN109033652A (en) * | 2018-08-02 | 2018-12-18 | 江苏艾佳家居用品有限公司 | A kind of indoor autoplacement method based on sliding window feature and regression forecasting |
| CN109598017A (en) * | 2018-10-18 | 2019-04-09 | 广东三维家信息科技有限公司 | A method of freely select wall intelligently to generate cabinet based on user |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
| CN109871604A (en) * | 2019-01-31 | 2019-06-11 | 浙江工商大学 | Indoor function zoning method based on depth confrontation network model |
| CN110096768A (en) * | 2019-04-16 | 2019-08-06 | 江苏艾佳家居用品有限公司 | A kind of method and system fast implementing kitchen autoplacement |
| CN110363853A (en) * | 2019-07-15 | 2019-10-22 | 贝壳技术有限公司 | Furniture puts scheme generation method, device and equipment, storage medium |
| CN110516208A (en) * | 2019-08-12 | 2019-11-29 | 深圳智能思创科技有限公司 | A kind of system and method extracted for PDF document table |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112163308A (en) * | 2020-10-13 | 2021-01-01 | 西安理工大学 | Adaptive guide design layout method |
| CN113744350A (en) * | 2021-08-31 | 2021-12-03 | 广州极点三维信息科技有限公司 | Cabinet structure identification method, device, equipment and medium based on single image |
| CN113743009A (en) * | 2021-08-31 | 2021-12-03 | 广州极点三维信息科技有限公司 | Cabinet type intelligent design method, device, equipment and medium based on representation learning |
| CN113744350B (en) * | 2021-08-31 | 2022-06-28 | 广州极点三维信息科技有限公司 | Cabinet structure identification method, device, equipment and medium based on single image |
| CN113743009B (en) * | 2021-08-31 | 2022-07-01 | 广州极点三维信息科技有限公司 | Cabinet type intelligent design method, device, equipment and medium based on representation learning |
| CN114722442A (en) * | 2022-06-08 | 2022-07-08 | 广东三维家信息科技有限公司 | Cabinet layout method and device, computer equipment and storage medium |
| WO2024098051A1 (en) * | 2022-11-04 | 2024-05-10 | Levin Jacqueline M | Methods and systems for space segmentation or organization |
| CN116070313A (en) * | 2022-12-08 | 2023-05-05 | 广州纬纶信息科技有限公司 | Cabinet intelligent storage layout generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111104704B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111104704A (en) | Cabinet internal layout design method, device and system and storage medium | |
| WO2021190127A1 (en) | Data processing method and data processing device | |
| CN114048331A (en) | Knowledge graph recommendation method and system based on improved KGAT model | |
| US9098941B2 (en) | Systems and methods for graphical layout | |
| CN111553480A (en) | Neural network searching method and device, computer readable medium and electronic equipment | |
| CN110264471A (en) | A kind of image partition method, device, storage medium and terminal device | |
| CN110826708B (en) | Method for realizing neural network model splitting by using multi-core processor and related product | |
| CN113129311B (en) | Label optimization point cloud instance segmentation method | |
| CN111860484B (en) | Region labeling method, device, equipment and storage medium | |
| CN108564541A (en) | A kind of image processing method and device | |
| CN109685806A (en) | Image significance detection method and device | |
| CN114255160A (en) | Data processing method, device, equipment and storage medium | |
| CN112837322A (en) | Image segmentation method and device, equipment and storage medium | |
| CN113127697B (en) | Method and system for optimizing graph layout, electronic device and readable storage medium | |
| CN114255353A (en) | Page significance element extraction method and system based on weighted hypergraph model | |
| EP3859611B1 (en) | Method, apparatus and device for updating convolutional neural network using gpu cluster | |
| CN117493920A (en) | Data classification method and device | |
| CN111353525A (en) | Modeling and missing value filling method for unbalanced incomplete data set | |
| CN111126395B (en) | Optimization method of selective search algorithm in R-CNN network and storage medium | |
| CN113822293A (en) | Model processing method, device and equipment for graph data and storage medium | |
| CN114548229A (en) | Training data augmentation method, device, equipment and storage medium | |
| Dandekar et al. | Multiobjective optimization of FPGA-based medical image registration | |
| CN113763240A (en) | Point cloud thumbnail generation method, device, equipment and storage medium | |
| CN117237241B (en) | Chromosome enhancement parameter adjustment method and device | |
| Aparco-Cardenas et al. | Object delineation by iterative dynamic trees |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |