CN111506940B - Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light - Google Patents
Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light Download PDFInfo
- Publication number
- CN111506940B CN111506940B CN201911283712.8A CN201911283712A CN111506940B CN 111506940 B CN111506940 B CN 111506940B CN 201911283712 A CN201911283712 A CN 201911283712A CN 111506940 B CN111506940 B CN 111506940B
- Authority
- CN
- China
- Prior art keywords
- furniture
- scene
- structured light
- module
- neural network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims abstract description 31
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 abstract description 9
- 241001465382 Physalis alkekengi Species 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a furniture, ornament and lamp integrated intelligent office method based on 3D structured light, which relates to the technical field of intelligent furniture layout and specifically comprises the following steps: 1) segmenting and collecting the acquired furniture scene 3D structured light data, 2) performing semantic segmentation on the 3D furniture scene structured light data, 3) automatically and intelligently arranging furniture in the 3D furniture scene after the semantic segmentation, 4) arranging 3D ornaments and 3D lamps after the 3D furniture is arranged. According to the 3D structured light furniture, ornament and lamp integrated intelligent office method, the 3D furniture, 3D ornament and 3D lamp integrated layout is realized in a 3D scene, the identification of height information is added in the identification of a 3D house type diagram, and the identification and understanding of information such as a 3D roof, a 3D wall body, a 3D roof height and the like are facilitated. Subsequently, also be of value to rationally overall arrangement 3D lamps and lanterns, 3D ornaments on 3D wall body, 3D roof, 3D furred ceiling.
Description
Technical Field
The invention relates to the technical field of intelligent furniture layout, in particular to an integrated intelligent layout method for furniture, ornaments and lamps based on 3D structured light.
Background
The existing household layout method mainly depends on manual design of designers or intervention of partial artificial intelligence algorithms, and the layout effect is not attractive due to individual difference and immaturity of the intelligent algorithms. Such as: the furniture layout style is single, the furniture layout is imperfect, the time consumption of the furniture layout is too long, and an ordinary user cannot experience the intelligent furniture layout effect in real time. The 3D intelligent layout system integrating the 3D structured light furniture, the ornaments and the lamps is used for realizing the effect of directly laying out the 3D furniture, the lamps and the ornaments in a 3D scene.
Disclosure of Invention
The invention aims to solve the technical problem of providing an integrated intelligent layout method of furniture, ornaments and lamps based on 3D structured light aiming at the defects of the background technology, which is beneficial to recognizing and understanding information such as 3D roofs, 3D walls, 3D roof heights and the like. Subsequently, also be of value to rationally overall arrangement 3D lamps and lanterns, 3D ornaments on 3D wall body, 3D roof, 3D furred ceiling.
The invention adopts the following technical scheme for solving the technical problems:
an integrated intelligent layout method for furniture, ornaments and lamps based on 3D structured light specifically comprises the following steps:
step 1, acquiring furniture scene 3D structured light data, including furniture scene 3D point cloud data and RDB-D depth map data;
step 2, receiving 3D structured light data of a furniture scene by using a neural network model, and generating 3D semantic segmentation information; the neural network comprises a general convolution kernel CNN, a sequence convolution kernel RNN and a sequence convolution kernel LSTM;
step 3, constructing a 3D furniture intelligent layout system by using a neural network model, wherein the 3D furniture intelligent layout system is composed of a reinforcement learning model and a CNN common convolution model, and the realization mode comprises a deep reinforcement model DQN;
step 4, after 3D furniture is well distributed in the 3D scene by using the neural network model, 3D ornaments and 3D lamps are continuously distributed in the 3D scene; the neural network model comprises a depth enhancement model DQN;
and 5, selecting the recorded layout state, and selecting TopN as a final result, wherein the TopN can be specified according to the requirements of the user.
As a further preferable scheme of the 3D structured light based furniture, ornament and lamp integrated intelligent layout method of the present invention, the step 2 is specifically as follows:
step 2.1, extracting scene 3D point cloud characteristics through a first characteristic extraction module;
2.2, extracting the RGB-D data characteristics of the scene through a second characteristic extraction module;
2.3, fusing the characteristics of 2.1 and 2.2 through a characteristic fusion module;
step 2.4, obtaining various segmentation information of the whole room through a semantic segmentation module, wherein the segmentation information comprises a door a, a window b, a wall c, a roof d and a suspended ceiling e;
and 2.5, obtaining 3D room categories including a 3D bedroom a, a 3D kitchen b, a 3D guest dining room c, a 3D study D and a 3D toilet e through semantic segmentation results and 2.3 and 2.4 results.
As a further preferable scheme of the 3D structured light-based furniture, ornament and lamp integrated intelligent layout method, the step 2.1 and the step 2.2 are realized by adopting a high-dimensional neural network extraction feature module.
As a further preferable scheme of the 3D structured light based furniture, ornament and lamp integrated intelligent layout method of the present invention, the step 2.3 employs a general multilayer CNN convolutional neural network.
As a further preferable scheme of the 3D structured light based furniture, ornament and lamp integrated intelligent layout method, the step 2.4 adopts a 3D scene semantic segmentation neural network.
As a further preferable scheme of the 3D structured light based furniture, ornament and lamp integrated intelligent layout method of the present invention, the step 3 is specifically as follows:
step 3.1, obtaining the result of semantic segmentation of the whole 3D scene of the house type, wherein the result comprises a 3D door x, a 3D wall y, a 3D window z, a 3D roof m and a 3D ceiling n;
step 3.2, obtaining semantic segmentation of the whole 3D scene based on the room type by using a general CNN module, wherein the semantic segmentation comprises a 3D bedroom a, a 3D kitchen b, a D guest dining room c, a 3D study D and a 3D toilet e;
3.3, intelligently distributing 3D furniture of each 3D room by using a depth tree and reinforcement learning combination module;
3.3.1, selecting a corresponding 3D furniture type for the corresponding 3D space by using a depth tree module, specifically selecting a 3D bed, a 3D storage cabinet and a 3D desk for a 3D bedroom;
and 3.3.2, automatically distributing the selected 3D furniture for the corresponding 3D space by using a reinforcement learning module.
Advantageous effects
According to the 3D structured light-based furniture, ornament and lamp integrated intelligent layout method, the 3D furniture, 3D ornament and 3D lamp integrated layout is realized in a 3D scene, the identification of height information is added in the identification of a 3D house type diagram, and the identification and understanding of information such as a 3D roof, a 3D wall body, a 3D roof height and the like are facilitated. Subsequently, also be of value to rationally overall arrangement 3D lamps and lanterns, 3D ornaments etc. on 3D wall body, 3D roof, 3D furred ceiling.
Drawings
FIG. 1 is a schematic diagram of an integrated intelligent layout method of furniture, ornaments and lamps based on 3D structured light according to the invention;
FIG. 2 is a 3D scene semantic segmentation, classification subsystem of the present invention;
FIG. 3 is a 3D furniture automation layout subsystem of the present invention;
FIG. 4 is a 3D accessory, 3D light fixture automated layout subsystem of the present invention;
FIG. 5 is a schematic diagram of a 3D point cloud extraction network in the 3D scene semantic segmentation subsystem according to the present invention;
FIG. 6 is a schematic diagram of an RGB-D information extraction network in the 3D scene semantic segmentation subsystem according to the present invention;
FIG. 7 is a depth tree module of the 3D furniture automation layout subsystem of the present invention;
FIG. 8 is a schematic diagram of a 3D scene semantic segmentation neural network according to the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An intelligent layout method based on integration of 3D structured light furniture, ornaments and lamps is shown in figure 1 and specifically comprises the following steps:
step 1, acquiring and collecting furniture scene 3D structured light data including but not limited to furniture scene 3D point cloud data O (1), RDB-D depth map data O (2) and the like.
Wherein, O1 and O2 are 3D scene information of the whole house type.
And 2, receiving multi-dimensional 3D scene data such as O (1), O (2) and the like by using a neural network model, and generating 3D semantic segmentation information. FIG. 2 is a 3D scene semantic segmentation, classification subsystem of the present invention, and FIG. 3 is a 3D furniture automation layout subsystem of the present invention;
one implementation is as follows:
and 2.1, extracting scene 3D point cloud characteristics through a characteristic extraction module 1.
And 2.2, extracting the RGB-D data characteristics of the scene through the characteristic extraction module 2.
And 2.3, fusing the characteristics of 2.1 and 2.2 through a characteristic fusion module.
And 2.4, obtaining various segmentation information of the door a, the window b, the wall c, the roof d, the suspended ceiling e and the like of the whole room through a semantic segmentation module.
And 2.5, obtaining 3D various room types such as a 3D bedroom a, a 3D kitchen b, a 3D guest dining room c, a 3D study room D, a 3D toilet e and the like through the semantic segmentation result and the 2.3 and 2.4 results.
Wherein step 2.1 and step 2.2 implement a module for extracting features including, but not limited to, using a high-dimensional neural network, such as the PointCNN network shown in fig. 5.
Wherein the step 2.3 implementation includes, but is not limited to, the use of a generic multi-layer CNN convolutional neural network.
Wherein, the step 2.4 includes but is not limited to adopting a 3D scene semantic segmentation neural network, and FIG. 6 is a schematic diagram of an RGB-D information extraction network in the 3D scene semantic segmentation subsystem. Such as the pointet network shown in fig. 8.
And 3, constructing a 3D furniture intelligent layout system by using the neural network model. The 3D spatial intelligent layout is composed of a reinforcement learning model and a CNN convolution model, and the implementation mode includes but is not limited to DQN and the like.
Step 3.1, extracting the characteristics of various 3D furniture, wherein the 3D furniture characteristic extraction module extracts the characteristics h (1) of each 3D furniture model Obj (1).
And 3.2, taking the result of the step 3.1, the result of the step 2.4 and the result of the step 2.5 as input, and obtaining an automatic layout scheme of the 3D furniture to be laid out in each 3D room through the depth tree model.
Implementations include, but are not limited to, depefiest, rnntree.
The depth tree recommendation model takes the characteristics h (1), the.
Wherein g (1).. g (n) is represented by each leaf node.
If realized by depofost, the specific implementation is as shown in fig. 7:
x is the contact operation of the input:
forest is two completely random tree forests, each completely random tree Forest comprises 1000 completely random trees, each tree is generated by randomly selecting a feature to segment each node of the tree, the tree grows until each leaf node only comprises the same type of example or no more than 10 examples, and finally the class probability of each 3D furniture combination of each room is output. 3.3 3 3.2 recommends 3.2 recommended classes of 3D furniture combinations to the appropriate location in the 3D room, neural network constructs including but not limited to DQN and the like.
In the case of the DQN model, as shown in figure 4,
the status module consists of the status of each 3D space, including, but not limited to, the position (x, y, z) of each 3D furniture, the orientation (c _1, c _2, c _3) of each 3D furniture, the number n of furniture already laid out in the room 3D model, the space proportion b occupied by the furniture already laid out in the room 3D model,
the environment module gives a 3D semantic state diagram D of each furniture in the room 3D model.
The reward module is composed of a multilayer convolutional network, and a function for calculating the difference between the current state S and the target state S' is the most rewarded, and is shown in formula 2:
R o (s, s') formula 2
The behavior module gives the probability that the agent is performing each action in one state, as shown in equation 3 below:
pi (a | s) ═ p (a | s) formula 3
Wherein the policy pi is given by the agent module,
the strategy selection and evaluation of the states s, s' are determined by the following state cost function V and strategy cost function Q, as shown in equations 4 and 5:
the state module gives out the state after the training algorithm is executed in each iteration, the environment module gives out a state diagram under the room environment, the behavior module makes a behavior, the reward module calculates a return value, and then the intelligent agent makes a strategy. And obtaining an optimal strategy, namely the optimal strategy of the 3D space home layout, after N iterations.
After 3D furniture has been laid out in the 3D room scene, 3D luminaires, 3D ornaments and the like continue to be laid out, which may be implemented by a neural network, the neural network comprising, but not limited to, DQN and the like.
In the case of the DQN model, the implementation is similar to step 3.3, but the difference is that the 3D space state will increase the 3D luminaire position (x, y, z), orientation (c _1, c _2, c _3), 3D jewelry position (x, y, z), orientation (c _1, c _2, c _3), luminaire specific weight b for the roof/ceiling and jewelry specific weight b for the wall for the room layout.
Step 4, after 3D furniture is well distributed in the 3D scene by using the neural network model, 3D ornaments and 3D lamps are continuously distributed in the 3D scene; the neural network model comprises a depth enhancement model DQN;
and 5, selecting the recorded layout state, and selecting TopN as a final result, wherein the TopN can be specified according to the requirements of the user.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention. While the embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (6)
1. An intelligent layout method based on integration of 3D structured light furniture, ornaments and lamps is characterized by comprising the following steps:
step 1, acquiring furniture scene 3D structured light data, including furniture scene 3D point cloud data and RDB-D depth map data;
step 2, receiving 3D structured light data of a furniture scene by using a neural network model, and generating 3D semantic segmentation information; the neural network comprises a general convolution kernel CNN, a sequence convolution kernel RNN and a sequence convolution kernel LSTM;
step 3, constructing a 3D furniture intelligent layout system by using a neural network model, wherein the 3D furniture intelligent layout system is composed of a reinforcement learning model and a CNN common convolution model, and the realization mode comprises a deep reinforcement model DQN;
step 4, after 3D furniture is well distributed in the 3D scene by using the neural network model, 3D ornaments and 3D lamps are continuously distributed in the 3D scene; the neural network model comprises a depth enhancement model DQN;
and 5, selecting the recorded layout state, and selecting TopN as a final result, wherein the TopN can be specified according to the requirements of the user.
2. The 3D structured light-based furniture, ornament and lamp integrated intelligent layout method according to claim 1, wherein the step 2 specifically comprises the following steps:
step 2.1, extracting scene 3D point cloud characteristics through a first characteristic extraction module;
2.2, extracting the RGB-D data characteristics of the scene through a second characteristic extraction module;
2.3, fusing the characteristics of 2.1 and 2.2 through a characteristic fusion module;
step 2.4, obtaining various segmentation information of the whole room through a semantic segmentation module, wherein the segmentation information comprises a door a, a window b, a wall c, a roof d and a suspended ceiling e;
and 2.5, obtaining 3D room categories including a 3D bedroom a, a 3D kitchen b, a 3D guest dining room c, a 3D study D and a 3D toilet e through semantic segmentation results and 2.3 and 2.4 results.
3. The 3D structured light based furniture, ornaments and lamp integrated intelligent layout method according to claim 2, wherein the step 2.1 and the step 2.2 are realized by a high-dimensional neural network extraction feature module.
4. The integrated intelligent layout method for furniture, ornaments and lamps based on 3D structured light according to claim 2, characterized in that the step 2.3 adopts a general multilayer CNN convolutional neural network.
5. The 3D structured light based furniture, ornaments and lamp integrated intelligent layout method according to claim 2, characterized in that step 2.4 employs a 3D scene semantic segmentation neural network.
6. The integrated intelligent layout method for furniture, ornaments and lamps based on 3D structured light according to claim 1, wherein the step 3 is specifically as follows:
step 3.1, obtaining the result of semantic segmentation of the whole 3D scene of the house type, wherein the result comprises a 3D door x, a 3D wall y, a 3D window z, a 3D roof m and a 3D ceiling n;
step 3.2, obtaining semantic segmentation of the whole 3D scene based on the room type by using a general CNN module, wherein the semantic segmentation comprises a 3D bedroom a, a 3D kitchen b, a D guest dining room c, a 3D study D and a 3D toilet e;
3.3, intelligently distributing 3D furniture of each 3D room by using a depth tree and reinforcement learning combination module;
3.3.1, selecting a corresponding 3D furniture type for the corresponding 3D space by using a depth tree module, specifically selecting a 3D bed, a 3D storage cabinet and a 3D desk for a 3D bedroom;
and 3.3.2, automatically distributing the selected 3D furniture for the corresponding 3D space by using a reinforcement learning module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911283712.8A CN111506940B (en) | 2019-12-13 | 2019-12-13 | Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911283712.8A CN111506940B (en) | 2019-12-13 | 2019-12-13 | Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111506940A CN111506940A (en) | 2020-08-07 |
CN111506940B true CN111506940B (en) | 2022-08-12 |
Family
ID=71874049
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911283712.8A Active CN111506940B (en) | 2019-12-13 | 2019-12-13 | Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111506940B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112800501A (en) * | 2021-01-15 | 2021-05-14 | 珠海新势力创建筑设计有限公司 | Method and device for automatically generating ceiling lamp model based on room information |
CN113052971B (en) * | 2021-04-09 | 2022-06-10 | 杭州群核信息技术有限公司 | Neural network-based automatic layout design method, device and system for indoor lamps and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108596102A (en) * | 2018-04-26 | 2018-09-28 | 北京航空航天大学青岛研究院 | Indoor scene object segmentation grader building method based on RGB-D |
CN110059690A (en) * | 2019-03-28 | 2019-07-26 | 广州智方信息科技有限公司 | Floor plan semanteme automatic analysis method and system based on depth convolutional neural networks |
-
2019
- 2019-12-13 CN CN201911283712.8A patent/CN111506940B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108596102A (en) * | 2018-04-26 | 2018-09-28 | 北京航空航天大学青岛研究院 | Indoor scene object segmentation grader building method based on RGB-D |
CN110059690A (en) * | 2019-03-28 | 2019-07-26 | 广州智方信息科技有限公司 | Floor plan semanteme automatic analysis method and system based on depth convolutional neural networks |
Also Published As
Publication number | Publication date |
---|---|
CN111506940A (en) | 2020-08-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Leach | Architecture in the age of artificial intelligence | |
Connolly | Perspectivism as a Way of Knowing in the Zhuangzi | |
CN111506940B (en) | Furniture, ornament and lamp integrated intelligent layout method based on 3D structured light | |
Von Stackelberg | The Roman garden: space, sense, and society | |
Bell | The simulation of branching patterns in modular organisms | |
Tutenel et al. | Generating consistent buildings: a semantic approach for integrating procedural techniques | |
CN108984618A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
Deane-Drummond | Joining in the dance: Catholic social teaching and ecology | |
Halbmayer | Introduction: Toward an anthropological understanding of the area between the Andes, Mesoamerica, and the Amazon | |
Ellen | Nuaulu religious practices; The frequency and reproduction of rituals in a Moluccan society | |
CN107220321A (en) | Solid threedimensional embodies in a kind of literary scape conversion method and its system | |
Bessey | Out of sorts: Making peace with an evolving faith | |
Ashraf | Taking place: Landscape in the architecture of Louis Kahn | |
Strang | Familiar forms: homologues, culture and gender in northern Australia | |
Blaviesciunaite | Cultural values embedded in building environmental performance assessment methods: a comparison of LEED-Canada and Japans CASBEE | |
Weber | A structured connectionist approach to direct inferences and figurative adjective-noun combinations | |
CN117706954B (en) | Method and device for generating scene, storage medium and electronic device | |
Ryan | That Seed Sets Time Ablaze | |
Sheu | The Call of the Hyperobjects | |
Leblanc | Stewards of Sustainability: A Theological Analysis of the Relationship Between the Anglican Church of Canada, The Climate Change Crisis, and Sustainability | |
Parker | Stop'n'Go | |
Semenov | Ecoempathic Design: Moving Beyond Biophilia With Brain Science | |
Nota et al. | When biophilic design meets restorative architecture: the Strambinello project | |
Hendricks | Playing-With the World: Toy Story's Aesthetics and Metaphysics of Play | |
Murray | Radical foundations in Bloomsbury |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 211100 floor 5, block a, China Merchants high speed rail Plaza project, No. 9, Jiangnan Road, Jiangning District, Nanjing, Jiangsu (South Station area) Applicant after: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. Address before: 211100 No. 18 Zhilan Road, Science Park, Jiangning District, Nanjing City, Jiangsu Province Applicant before: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |