CN114241129B - Indoor scene layout method and device, electronic equipment and storage medium - Google Patents
Indoor scene layout method and device, electronic equipment and storage mediumInfo
- Publication number
- CN114241129B CN114241129B CN202111505856.0A CN202111505856A CN114241129B CN 114241129 B CN114241129 B CN 114241129B CN 202111505856 A CN202111505856 A CN 202111505856A CN 114241129 B CN114241129 B CN 114241129B
- Authority
- CN
- China
- Prior art keywords
- evaluation value
- scene layout
- node
- dimensional scene
- obtaining
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/04—Architectural design, interior design
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Structural Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Architecture (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本申请实施例提供一种室内场景布局方法、装置、电子设备及存储介质，其中，该方法包括：获取物体节点，根据物体节点构建多边形数据结构；获取墙体信息，根据墙体信息对多边形数据结构进行规划处理，得到二维场景布局；将二维场景布局降维为一维场景布局；根据一维场景布局获得综合约束评价值，若综合约束评价值大于阈值，则根据一维场景布局生成室内场景布局，若综合约束评价值小于或者等于阈值，则重新获得新的一维场景布局。实施本申请实施例，可以将二维数据转换成一维数据，节约了计算时间，不会受到数据差异的影响，同时得到的室内场景布局更加符合实际。
The embodiment of the present application provides an indoor scene layout method, device, electronic device and storage medium, wherein the method includes: obtaining object nodes, constructing a polygonal data structure according to the object nodes; obtaining wall information, planning and processing the polygonal data structure according to the wall information, and obtaining a two-dimensional scene layout; reducing the two-dimensional scene layout to a one-dimensional scene layout; obtaining a comprehensive constraint evaluation value according to the one-dimensional scene layout, if the comprehensive constraint evaluation value is greater than a threshold, generating an indoor scene layout according to the one-dimensional scene layout, if the comprehensive constraint evaluation value is less than or equal to the threshold, re-obtaining a new one-dimensional scene layout. By implementing the embodiment of the present application, two-dimensional data can be converted into one-dimensional data, which saves calculation time and will not be affected by data differences. At the same time, the obtained indoor scene layout is more in line with reality.
Description
Technical Field
The present application relates to the field of indoor design technologies, and in particular, to an indoor scene layout method, an apparatus, an electronic device, and a computer readable storage medium.
Background
At present, the indoor design layout method is generally implemented by adopting an optimization-based method or a deep learning-based method, however, both methods have certain limitations.
The optimization-based method generally does not consider constraint conditions, randomly generates an initial solution, and then uses an optimization algorithm to adjust the scene layout so as to enable the scene layout to meet basic layout constraints such as adjacent relations and the like as far as possible. This makes the iterative solution process using an optimization algorithm extremely time consuming and limited in optimization capacity, and does not truly satisfy the given constraints.
Deep learning-based methods typically first build a data set with layout structure and then encode layout features in the data set into a deep learning model by training on the data set to generate the layout. This makes reasonable results impossible to obtain when the data in the data set is widely different, and high-level constraints such as room adjacency, room size constraints, space rationality, etc. cannot be handled.
Disclosure of Invention
An object of the embodiments of the present application is to provide an indoor scene layout method, apparatus, electronic device, and computer readable storage medium, which can convert two-dimensional data into one-dimensional data, solve the problem of complex constraint of the whole indoor scene layout, and can not be affected by data differences, and can reduce computation time.
In a first aspect, an embodiment of the present application provides an indoor scene layout method, where the method includes:
acquiring object nodes, and constructing a polygonal data structure according to the object nodes;
Acquiring wall information, and planning the polygon data structure according to the wall information to obtain a two-dimensional scene layout;
Reducing the dimension of the two-dimensional scene layout into a one-dimensional scene layout;
And obtaining a comprehensive constraint evaluation value according to the one-dimensional scene layout, generating an indoor scene layout according to the one-dimensional scene layout if the comprehensive constraint evaluation value is larger than a threshold value, and obtaining a new one-dimensional scene layout again if the comprehensive constraint evaluation value is smaller than or equal to the threshold value.
In the implementation process, the characteristics of the object nodes are gathered by utilizing the polygon data mechanism, the method is not limited to a common picture form, the object nodes are combined with wall information to obtain two-dimensional scene layout, then the indoor scene layout is obtained through one-dimensional scene layout, the calculation time is saved, and meanwhile, the obtained indoor scene layout is more practical.
Further, the step of obtaining the object node and constructing a polygon data structure according to the object node includes:
Obtaining boundary sub-nodes and remaining object sub-nodes in the object nodes;
And inserting the rest object child nodes into the boundary child nodes to obtain the polygonal data structure.
In the implementation process, the polygon data structure can adapt to scenes with different scales, the generation efficiency on the scenes with different scales can not be different due to different scene scales, and meanwhile, the layout of the special-shaped indoor scene can be generated by using the polygon data structure.
Further, the step of obtaining wall information, planning the polygon data structure according to the wall information to obtain a two-dimensional scene layout includes:
obtaining the attachment relation between the wall body and the object node according to the wall body information;
and planning the polygon data structure according to the attachment relation to obtain the two-dimensional scene layout.
In the implementation process, the attachment relation contains the wall information and the connection data between the object nodes, so that the object nodes can be ensured to attach to the correct wall, and confusion between the wall and the object nodes can not be caused.
Further, the step of reducing the dimension of the two-dimensional scene layout to a one-dimensional scene layout includes:
acquiring two-dimensional coordinates in the wall information in the two-dimensional scene layout;
carrying out boundary topology isomorphism treatment on the two-dimensional coordinates to obtain one-dimensional coordinates;
And obtaining the one-dimensional scene layout according to the one-dimensional coordinates.
In the implementation process, the two-dimensional coordinates are converted into the one-dimensional coordinates, so that the dimension is reduced, the complex scene layout is possible, the indoor scene layout is not influenced by multi-dimensional data when being generated, and the rationality of the indoor scene layout is ensured.
Further, the step of obtaining the comprehensive constraint evaluation value according to the one-dimensional scene layout includes:
Obtaining a space utilization rate evaluation value, a relation constraint evaluation value, a movable space evaluation value and an evacuable evaluation value according to the one-dimensional scene layout;
And obtaining the comprehensive constraint evaluation value according to the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value.
In the implementation process, the comprehensive constraint evaluation of the one-dimensional scene layout can ensure the rationality of the scene layout, eliminate the potential safety hazard existing in the indoor scene layout generation process, and ensure the safety and usability of the indoor scene layout.
Further, a space utilization evaluation value, a relationship constraint evaluation value, a movable space evaluation value, and an evacuable evaluation value are obtained from the one-dimensional scene layout according to the following formula:
the utilization rate evaluation value is as follows:
wherein, R space is the space utilization evaluation value, S total is the total area of the scene, and RN is the wall-leaning room node and the free room node in the remaining object child nodes;
The relationship constraint evaluation value is:
Wherein R neighboor is the relationship constraint evaluation value, RCNS is a room container node in the remaining object child nodes, RNS is a room node in the remaining object child nodes, RN k is a room node k in the remaining object child nodes, and Pair is an adjacent relationship indication function;
movable spatial evaluation value:
wherein R move is the movable space evaluation value, and CA is a closed region in the scene;
Evacuable evaluation value:
Wherein R escape is the evacuable evaluation value, ECA is the evacuable area in the enclosed area, and S total is the total area of the scene.
In the implementation process, the space utilization rate evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value can evaluate the one-dimensional scene layout from multiple directions and multiple angles, so that the rationality of the one-dimensional scene layout is ensured, and the one-dimensional scene layout can generate the indoor scene layout.
Further, the step of obtaining the comprehensive constraint evaluation value from the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value, and the evacuable evaluation value includes:
acquiring an evaluation index R other;
obtaining the comprehensive constraint evaluation value according to the evaluation index, the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value:
Rtotal＝λspace·Rspace+λneighboor·Rneighboor+λmove·Rmove+λescape·Rescape+λother·Rother;
Wherein, lambda space is the utilization rate evaluation weight value, lambda neighboor is the relation constraint evaluation weight value, lambda move is the movable space evaluation weight value, and lambda escape is the evacuable evaluation weight value.
In the implementation process, the comprehensive constraint evaluation value can embody the space utilization, relation constraint, evadability and mobility of the indoor scene layout, so that the indoor scene layout is in line with the actual use.
In a second aspect, an embodiment of the present application further provides an indoor scene layout apparatus, where the apparatus includes:
The construction module is used for acquiring object nodes and constructing a polygonal data structure according to the object nodes;
the planning module is used for acquiring wall information, planning the polygon data structure according to the wall information and obtaining a two-dimensional scene layout;
The conversion module is used for reducing the dimension of the two-dimensional scene layout into a one-dimensional scene layout;
The generating module is used for obtaining a comprehensive constraint evaluation value according to the one-dimensional scene layout, generating an indoor scene layout according to the one-dimensional scene layout if the comprehensive constraint evaluation value is larger than a threshold value, and obtaining a new one-dimensional scene layout again if the comprehensive constraint evaluation value is smaller than or equal to the threshold value.
In the implementation process, the characteristics of the object nodes are gathered by utilizing the polygon data mechanism, the method is not limited to a common picture form, the object nodes are combined with wall information to obtain two-dimensional scene layout, then the indoor scene layout is obtained through one-dimensional scene layout, the calculation time is saved, and meanwhile, the obtained indoor scene layout is more practical.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of the first aspects when the computer program is executed.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where instructions are stored, when the instructions are executed on a computer, to cause the computer to perform the method according to any one of the first aspects.
In a fifth aspect, embodiments of the present application provide a computer program product, which when run on a computer causes the computer to perform the method according to any of the first aspects.
Additional features and advantages of the disclosure will be set forth in the description which follows, or in part will be obvious from the description, or may be learned by practice of the techniques of the disclosure.
And can be implemented in accordance with the teachings of the specification, the following detailed description of the preferred embodiments of the application, taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of an indoor scene layout method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a polygon data structure according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an attachment relationship according to an embodiment of the present application;
FIG. 4 is a schematic diagram of coordinate transformation according to an embodiment of the present application;
Fig. 5 is a schematic diagram of indoor scene layout according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an indoor scene layout device according to an embodiment of the present application;
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.
It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
The following describes in further detail the embodiments of the present application with reference to the drawings and examples. The following examples are illustrative of the application and are not intended to limit the scope of the application.
Example 1
Fig. 1 is a flow chart of an indoor scene layout method according to an embodiment of the present application, as shown in fig. 1, the method includes:
s1, acquiring object nodes, and constructing a polygonal data structure according to the object nodes;
S2, obtaining wall information, and planning and processing the polygon data structure according to the wall information to obtain a two-dimensional scene layout;
S3, reducing the dimension of the two-dimensional scene layout into a one-dimensional scene layout;
S4, obtaining a comprehensive constraint evaluation value according to the one-dimensional scene layout, generating an indoor scene layout according to the one-dimensional scene layout if the comprehensive constraint evaluation value is larger than a threshold value, and obtaining a new one-dimensional scene layout again if the comprehensive constraint evaluation value is smaller than or equal to the threshold value.
Taking the embodiment as an example, the characteristics of the object nodes are gathered by utilizing the polygon data mechanism, the method is not limited to a common picture form, the object nodes are combined with wall information to obtain two-dimensional scene layout, then the indoor scene layout is obtained through one-dimensional scene layout, the calculation time is saved, and meanwhile, the obtained indoor scene layout is more practical.
Illustratively, S1 further comprises:
obtaining boundary sub-nodes and residual object sub-nodes in the object nodes;
and inserting the rest object child nodes into the boundary child nodes to obtain the polygonal data structure.
Taking the embodiment as an example, the polygon data structure can adapt to scenes with different scales, the generation efficiency on the scenes with different scales can not cause differences due to different scene scales, and meanwhile, the polygon data structure can be used for generating the layout of the abnormal indoor scene.
A basic data unit for describing a single Object in an indoor scene, called Object Node (ON), optionally comprising:
1. the world child node is used for creating object nodes and constructing an initial root node of the attachment relation;
2. The outer wall body child node is a node for storing the initial outer wall body outline of the indoor scene;
3. the inner wall body sub-node is used for storing the inner wall body outline of the indoor scene, and the inner wall body comprises a bearing wall, an elevator shaft, a fire fighting channel, other fixed walls and the like;
4. a room container sub-node for storing the nodes of the room group with adjacent relations, wherein the nodes comprise one or more wall-leaning room sub-nodes or free room sub-nodes with adjacent relations;
5. The wall-leaning room sub-node is used for storing the wall-leaning room outline with the attachment relation with the inner wall body and the outer wall body;
6. free room sub-node, which is used for storing the node of the free room outline which has no attachment relation with the inner wall and the outer wall, wherein the free room can be a semi-open area such as an open conference room, an open negotiation room, a bar counter and the like;
7. A team sub-node for storing a node having an attachment relationship with a wall-next room sub-node or a free room sub-node, the node comprising a minimum outline of one or more regular workspace sub-nodes;
8. A workspace sub-node for storing nodes having an attachment relationship with team sub-nodes that contain a minimum outline of one or more furniture sub-nodes;
9. a furniture sub-node for storing the position of a single furniture having an attachment relationship with the workspace node and simplifying the node of the outer contour;
10. the space sub-node is used for storing the position information of the polygon corresponding to the outline of the object node;
11. boundary sub-node is a node for storing the position information of a certain edge in the outline of the object node.
The remaining object children nodes include children nodes in other object nodes except the boundary children nodes, and as shown in fig. 2, are polygonal data structures formed by a plurality of children nodes in the object nodes.
S2 further comprises:
obtaining the attachment relation between the wall body and the object node according to the wall body information;
And planning the polygon data structure according to the attachment relation to obtain the two-dimensional scene layout.
Taking the embodiment as an example, the attachment relation contains the wall information and the connection data between the object nodes, so that the object nodes can be ensured to attach to the correct wall, and disorder between the wall and the object nodes can not be caused.
The wall is divided into two different types, one is a wall which changes along with the position of the room, called a room wall, which is a wall which must be generated along with the room due to the addition of the room in the scene, and the positions of the walls change along with the room when the position of the room changes, and the other is a wall which is independent of the position of the room, called a fixed wall, which always exists regardless of the position of the room in the scene, such as the initial outline of the scene, an elevator shaft, a bearing wall, and the like.
For a reasonable indoor scene layout, all rooms are always attached to at least one fixed wall.
For example, as shown in fig. 3, for the World coordinate system (World Axis) at the left side of the figure, firstly, an Outer contour (Outer Wall) boundary is added, the coordinate system where the Outer contour is located is ON1 AIW, after the Outer contour is added, four boundary sub-nodes BN1, BN2, BN3, BN4 and a space sub-node SN1 are created, for the boundary sub-node BN1 (the boundary sub-node is ON1-BN1 for convenience in the figure), the coordinate system where the boundary sub-node BN1 is ON1-BN1 AIW, a Wall-leaning room ON2 (the boundary sub-node is ON1-BN1-ON2 for convenience in the figure) is added, the coordinate system where the Wall-leaning room is ON the X Axis of the boundary sub-node BN1, the directions of the two coordinate systems remain the same, further, the Wall-leaning room ON2 can only slide ON the boundary of the Outer contour, and the coordinate system is always in the same direction as the boundary sub-node, and the coordinate system is ON the right side of the boundary sub-node.
Further, a two-dimensional scene layout is obtained through the attachment relation, a lattice set is constructed for covering the whole scene and sniffing the position coordinates of the unused area, the shortest distance between any two points in the lattice becomes a free room generation error (the error value can be adaptively adjusted according to the scene size), the two-dimensional scene layout is obtained by dividing according to the state of each point in the lattice, a maximum and unused regular rectangular area is obtained, a free room sub-node and a plurality of team sub-nodes are generated on the largest and unused rectangular area, and then the process is repeated until the unused area with a proper size cannot be found in the whole scene.
Through the generation process, the unused area in the whole scene can be reduced as much as possible, so that the space utilization rate of the whole scene is greatly improved.
S3 further comprises:
acquiring two-dimensional coordinates in the wall information in a two-dimensional scene layout;
carrying out boundary topology isomorphism treatment on the two-dimensional coordinates to obtain one-dimensional coordinates;
And obtaining a one-dimensional scene layout according to the one-dimensional coordinates.
As shown in fig. 4, a schematic diagram of converting two-dimensional coordinates into one-dimensional coordinates is shown, the outer wall and the inner wall on the left side in the diagram are respectively converted into two one-dimensional line segments, the length of the line segments is equal to the total length of the outline of the wall corresponding to the line segments, the generation of boundary lines of the room container is performed on the line segments, and each boundary line corresponds to the attachment position of a child node of the room container. The boundary topology is isomorphic, and can reduce the two-dimensional coordinates into one-dimensional coordinates.
Obtaining a one-dimensional scene layout according to the one-dimensional coordinates, searching the position corresponding to the boundary line and all other room container outlines at the left side of the graph by shortest distance, thus obtaining a maximum height value of the collision-free room container, ensuring that the room container is not overlapped with any other room container, finally comparing the maximum height value with the designated height of the room container, taking a smaller value as the actual height of the room container, converting the actual height of the room container into the actual room container at the left side of the graph, and adding the actual room container to boundary sub-nodes of the corresponding wall body.
Taking the embodiment as an example, the two-dimensional coordinates are converted into one-dimensional coordinates, so that the dimension is reduced, the complex scene layout is possible, the indoor scene layout is not affected by multi-dimensional data when being generated, and the rationality of the indoor scene layout is ensured.
S4 further comprises:
further, the step of obtaining the comprehensive constraint evaluation value according to the one-dimensional scene layout includes:
Obtaining a space utilization rate evaluation value, a relation constraint evaluation value, a movable space evaluation value and an evacuable evaluation value according to the one-dimensional scene layout;
And obtaining a comprehensive constraint evaluation value according to the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value.
Taking the embodiment as an example, the comprehensive constraint evaluation on the one-dimensional scene layout can ensure the rationality of the scene layout, eliminate the potential safety hazard existing in the generation process of the indoor scene layout, and ensure the safety and usability of the indoor scene layout.
Further, a space utilization evaluation value, a relationship constraint evaluation value, a movable space evaluation value, and an evacuable evaluation value are obtained from a one-dimensional scene layout according to the following formula:
the utilization rate evaluation value is as follows:
Wherein R space is a space utilization evaluation value, S total is the total area of the scene, and RN is a wall-leaning room node and a free room node in the child nodes of the rest objects;
The relationship constraint evaluation value is:
Wherein R neighboor is a relationship constraint evaluation value, RCNS is a room container node in the remaining object child nodes, RNS is a room node in the remaining object child nodes, RN k is a room node k in the remaining object child nodes, pair is an adjacency relationship indication function, and due to existence of the room container nodes, whether adjacency relationship of rooms satisfies constraint rules of adjacency relationship needs to be judged by judging whether rooms are in the same room container, when two room nodes are defined as adjacent rooms, a return value 1 of R neighboor function is returned, otherwise, a return value 0 is returned.
Movable spatial evaluation value:
Wherein R move is a movable space evaluation value, and CA is a closed region in the scene;
Since all non-passable areas in the scene are exactly covered by furniture sub-nodes, it is necessary to judge the connectivity of all areas except furniture sub-nodes, i.e. to evaluate the mobility in the scene.
For the example layout on the left side of the figure, firstly, all furniture sub-nodes are clustered according to connectivity to obtain a plurality of obstacle polygon sets (Obstacle Polygon Set) which cannot cross furniture and are not wanted to cross each other, as shown in the middle part of the figure, whether each obstacle polygon (Obstacle Polygon) intersects with at least two different walls is judged, if yes, intersection information of the intersected walls and the intersection information is recorded, all inner walls are converted into nodes by recording the information, and the intersection information is transmitted, so that the segmentation of the outer walls is obtained, and as shown in the right side part of the figure, the whole scene can be quickly found to be isolated into a plurality of Closed areas (Closed areas) through the intersection result.
Evacuable evaluation value:
Wherein R escape is an evacuable evaluation value, ECA is an evacuable region in the closed region, and S total is a total area of the scene.
Taking the embodiment as an example, the space utilization rate evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value can evaluate the one-dimensional scene layout from multiple directions and multiple angles, so that the rationality of the one-dimensional scene layout is ensured, and the one-dimensional scene layout can generate the indoor scene layout.
Further, the step of obtaining the comprehensive constraint evaluation value according to the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value includes:
acquiring an evaluation index R other;
obtaining a comprehensive constraint evaluation value according to the evaluation index, the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value:
Rtotal＝λspace·Rspace+λneighboor·Rneighboor+λmove·Rmove+λescape·Rescape+λother·Rother;
wherein λ space is a utilization rate evaluation weight value, that is, a weight of the utilization rate evaluation value, λ neighboor is a relationship constraint evaluation weight value, that is, a weight of the relationship constraint evaluation value, λ move is a movable space evaluation weight value, that is, a weight of the movable space evaluation weight value, λ escape is an evadability evaluation weight value, that is, a weight of the evadability evaluation weight value, and λ space+λneighboor+λmove+λescape =1 is satisfied.
Taking the embodiment as an example, the comprehensive constraint evaluation value can embody the space utilization, relation constraint, evadability and mobility of the indoor scene layout, so that the indoor scene layout accords with the actual use.
Alternatively, the process of generating the indoor scene layout according to the one-dimensional scene layout may be performed according to reinforcement learning, that is, a process of interacting an Agent (Agent) with the surrounding Environment, and when an Environment (Environment) is given, it is required to set how the Agent interacts with the Environment, that is, create an Action Space (Action Space), the Agent changes the state of the Environment by selecting an Action in the Action Space and executing the Action, and then evaluate the selected Action of the Agent for the change of the Environment and tell the Agent about the evaluation and a new state (Observations) of the current Environment, and the Agent selects the next Action according to the two data until the round is ended. By repeating this process, we can let the agent learn how to choose the action by telling him the reward to maximize this reward.
The boundary line generating system based on the room container defines a single-step action of reinforcement learning, namely, a boundary line is inserted into line segments corresponding to all walls each time, a target height is set, and after the boundary line is inserted for a plurality of times, a complete scene layout can be obtained.
After each single-step action is executed, comprehensive constraint evaluation is carried out on the current scene layout to obtain a comprehensive constraint evaluation value, and the comprehensive constraint evaluation is used as the score of the reinforcement learning reward function to promote the comprehensive constraint evaluation to gradually generate the indoor scene layout meeting the requirements.
After a large amount of training, the intelligent agent can generate a reasonable indoor scene layout which meets comprehensive constraint evaluation as far as possible according to object nodes and wall information, and even if strong conflict exists between the provided object nodes and wall information, a reasonable result can be obtained without solving failure.
Example two
In order to perform a corresponding method of the above embodiment to achieve the corresponding functions and technical effects, an indoor scene layout apparatus is provided below, as shown in fig. 6, which includes:
the construction module 1 is used for acquiring object nodes and constructing a polygonal data structure according to the object nodes;
The planning module 2 is used for acquiring wall information, and planning the polygon data structure according to the wall information to obtain a two-dimensional scene layout;
The conversion module 3 is used for reducing the dimension of the two-dimensional scene layout into a one-dimensional scene layout;
The generating module 4 is configured to obtain a comprehensive constraint evaluation value according to the one-dimensional scene layout, generate an indoor scene layout according to the one-dimensional scene layout if the comprehensive constraint evaluation value is greater than a threshold value, and retrieve a new one-dimensional scene layout if the comprehensive constraint evaluation value is less than or equal to the threshold value.
Further, the building module 1 is further configured to:
obtaining boundary sub-nodes and residual object sub-nodes in the object nodes;
and inserting the rest object child nodes into the boundary child nodes to obtain the polygonal data structure.
Further, the planning module 2 is further configured to:
obtaining the attachment relation between the wall body and the object node according to the wall body information;
And planning the polygon data structure according to the attachment relation to obtain the two-dimensional scene layout.
Further, the conversion module 3 is further configured to:
Acquiring two-dimensional coordinates in wall information in a two-dimensional scene layout;
carrying out boundary topology isomorphism treatment on the two-dimensional coordinates to obtain one-dimensional coordinates;
And obtaining a one-dimensional scene layout according to the one-dimensional coordinates.
Further, the generating module 4 is further configured to:
Obtaining a space utilization rate evaluation value, a relation constraint evaluation value, a movable space evaluation value and an evacuable evaluation value according to the one-dimensional scene layout;
And obtaining a comprehensive constraint evaluation value according to the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value.
The utilization rate evaluation value is as follows:
Wherein R space is a space utilization evaluation value, S total is the total area of the scene, and RN is a wall-leaning room node and a free room node in the child nodes of the rest objects;
The relationship constraint evaluation value is:
Wherein R neighboor is a relationship constraint evaluation value, RCNS is a room container node in the remaining object child node, RNS is a room node in the remaining object child node, RN k is a room node k in the remaining object child node, and Pair is an adjacent relationship indication function;
movable spatial evaluation value:
Wherein R move is a movable space evaluation value, and CA is a closed region in the scene;
Evacuable evaluation value:
Wherein R escape is an evacuable evaluation value, ECA is an evacuable region in the closed region, and S total is a total area of the scene.
Acquiring an evaluation index R other;
obtaining a comprehensive constraint evaluation value according to the evaluation index, the space utilization evaluation value, the relation constraint evaluation value, the movable space evaluation value and the evacuable evaluation value:
Rtotal＝λspace·Rspace+λneighboor·Rneighboor+λmove·Rmove+λescape·Rescape+λother·Rother;
Wherein, lambda space is the utilization rate evaluation weight value, lambda neighboor is the relation constraint evaluation weight value, lambda move is the movable space evaluation weight value, and lambda escape is the evacuable evaluation weight value.
The indoor scene layout device described above may implement the method of the first embodiment described above. The options in the first embodiment described above also apply to this embodiment, and are not described in detail here.
The rest of the embodiments of the present application may refer to the content of the first embodiment, and in this embodiment, no further description is given.
Example III
The embodiment of the application provides an electronic device, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the indoor scene layout method of the first embodiment.
Alternatively, the electronic device may be a server.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the application. The electronic device may include a processor 71, a communication interface 72, a memory 73, and at least one communication bus 74. Wherein the communication bus 74 is used to enable direct connection communication of these components. The communication interface 72 of the device in the embodiment of the present application is used for signaling or data communication with other node devices. The processor 71 may be an integrated circuit chip with signal processing capabilities.
The processor 71 may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc., or may be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. The general purpose processor may be a microprocessor or the processor 71 may be any conventional processor or the like.
The Memory 73 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 73 has stored therein computer readable instructions which, when executed by the processor 71, may cause the apparatus to perform the steps described above in relation to the embodiment of the method of fig. 1.
Optionally, the electronic device may further include a storage controller, an input-output unit. The memory 73, the memory controller, the processor 71, the peripheral interface, and the input/output unit are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically coupled to each other via one or more communication buses 74. The processor 71 is arranged to execute executable modules stored in the memory 73, such as software functional modules or computer programs comprised by the device.
The input-output unit is used for providing the user with the creation task and creating the starting selectable period or the preset execution time for the task so as to realize the interaction between the user and the server. The input/output unit may be, but is not limited to, a mouse, a keyboard, and the like.
It will be appreciated that the configuration shown in fig. 7 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 7, or have a different configuration than shown in fig. 7. The components shown in fig. 7 may be implemented in hardware, software, or a combination thereof.
In addition, the embodiment of the application also provides a computer readable storage medium storing a computer program, which when executed by a processor, implements the indoor scene layout method of the first embodiment.
The present application also provides a computer program product which, when run on a computer, causes the computer to perform the method described in the method embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes various media capable of storing program codes such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application. It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
Claims (6)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111505856.0A CN114241129B (en) | 2021-12-10 | 2021-12-10 | Indoor scene layout method and device, electronic equipment and storage medium |
| PCT/CN2022/071858 WO2023103147A1 (en) | 2021-12-10 | 2022-01-13 | Indoor scene layout method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111505856.0A CN114241129B (en) | 2021-12-10 | 2021-12-10 | Indoor scene layout method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114241129A CN114241129A (en) | 2022-03-25 |
| CN114241129B true CN114241129B (en) | 2025-07-25 |
Family
ID=80754700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111505856.0A Active CN114241129B (en) | 2021-12-10 | 2021-12-10 | Indoor scene layout method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114241129B (en) |
| WO (1) | WO2023103147A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274423B (en) * | 2023-08-23 | 2024-06-04 | 瑞庭网络技术（上海）有限公司 | House source information processing method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111274627A (en) * | 2019-12-25 | 2020-06-12 | 江苏艾佳家居用品有限公司 | Automatic kitchen layout method and device based on nonlinear optimization and computer equipment |
| CN113486436A (en) * | 2021-09-08 | 2021-10-08 | 深圳须弥云图空间科技有限公司 | Soft installation design method, device, equipment and storage medium based on tree structure |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003345859A (en) * | 2002-05-27 | 2003-12-05 | Misawa Homes Co Ltd | Method and system for room layout plan acquisition and recording medium |
| US8140989B2 (en) * | 2009-02-19 | 2012-03-20 | Kimberly-Clark Worldwide, Inc. | Virtual room use simulator and room planning system |
| JP6139089B2 (en) * | 2012-10-02 | 2017-05-31 | 株式会社東芝 | Design support apparatus and design support method |
| CN106484955B (en) * | 2016-09-14 | 2019-05-14 | 中国科学院计算技术研究所 | A kind of indoor arrangement evaluation method and system based on Voronoi diagram |
| CN107424161B (en) * | 2017-04-25 | 2021-03-02 | 南京邮电大学 | A Coarse-to-fine Image Layout Estimation Method for Indoor Scenes |
| US10026218B1 (en) * | 2017-11-01 | 2018-07-17 | Pencil and Pixel, Inc. | Modeling indoor scenes based on digital images |
| CN109064545B (en) * | 2018-06-06 | 2020-07-07 | 贝壳找房(北京)科技有限公司 | Method and device for data acquisition and model generation of house |
| US10839606B2 (en) * | 2018-12-28 | 2020-11-17 | National Tsing Hua University | Indoor scene structural estimation system and estimation method thereof based on deep learning network |
| CN111598972B (en) * | 2020-04-03 | 2021-06-29 | 深圳大学 | Method, device, computer equipment and storage medium for generating floor plan |
| CN112907750A (en) * | 2021-03-05 | 2021-06-04 | 齐鲁工业大学 | Indoor scene layout estimation method and system based on convolutional neural network |
| CN113642065B (en) * | 2021-06-28 | 2024-03-12 | 中国地质大学（武汉） | Indoor semi-automatic drawing and modeling method based on DXF vector plan |
-
2021
- 2021-12-10 CN CN202111505856.0A patent/CN114241129B/en active Active
-
2022
- 2022-01-13 WO PCT/CN2022/071858 patent/WO2023103147A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111274627A (en) * | 2019-12-25 | 2020-06-12 | 江苏艾佳家居用品有限公司 | Automatic kitchen layout method and device based on nonlinear optimization and computer equipment |
| CN113486436A (en) * | 2021-09-08 | 2021-10-08 | 深圳须弥云图空间科技有限公司 | Soft installation design method, device, equipment and storage medium based on tree structure |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114241129A (en) | 2022-03-25 |
| WO2023103147A1 (en) | 2023-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | Multi-agent plan reconfiguration under local LTL specifications | |
| EP3201709B1 (en) | Method and system for determining a path of an object for moving from a starting state to an end state set avoiding one or more obstacles | |
| Barbosa et al. | Guiding autonomous exploration with signal temporal logic | |
| CN114241129B (en) | Indoor scene layout method and device, electronic equipment and storage medium | |
| Latip et al. | Optimal path planning using equilateral spaces oriented visibility graph method | |
| US12299350B2 (en) | Generating designs for multi-family housing projects using physical simulations of design elements | |
| US20250053179A1 (en) | Pathfinding apparatus, pathfinding method, and non-transitory computer-readable storage medium | |
| Kaiser et al. | Centered parameterizations and dependence limitations in Markov random field models | |
| Lupascu et al. | Path planning for autonomous drones using 3d rectangular cuboid decomposition | |
| Chand et al. | A two-tiered global path planning strategy for limited memory mobile robots | |
| CN114186306A (en) | Customizable reinforcement learning for post placement in structural design | |
| KR20130133591A (en) | A method and apparatus for segmenting a grid map into a plurality of rooms | |
| Deshpande et al. | An algorithm to create model file for Partially Observable Markov Decision Process for mobile robot path planning | |
| Yoon | Single agent control for multi-agent dynamical consensus systems | |
| Perkins et al. | Field D* path-finding on weighted triangulated and tetrahedral meshes | |
| Surynek | Lazy modeling of variants of token swapping problem and multi-agent path finding through combination of satisfiability modulo theories and conflict-based search | |
| Khanal et al. | Learning Augmented, Multi-Robot Long-Horizon Navigation in Partially Mapped Environments | |
| Schuppe | Assumptions in synthesis: An approach to multi-agent planning from spatio-temporal specifications | |
| Surynek | Swarms of mobile agents: From discrete to continuous movements in multi-agent path finding | |
| Nadel | Routing under constraints | |
| Omer et al. | Semantic Path Planning for Heterogeneous Robots from Building Digital Twin Data | |
| Yao et al. | Accelerating multi-agent path finding based on roadmap construction in non-grid environment | |
| Karnad et al. | Modeling human motion patterns for multi-robot planning | |
| Kakooee et al. | Illuminating Spaces: Deep Reinforcement Learning and Laser-Wall Partitioning for Architectural Layout Generation | |
| KR101558174B1 (en) | Spatial reasoner for inferring the topological and directional relationships between two geo-entities, method and recording medium |
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 |