CN110598333B - Determination method and device for light source position and electronic equipment - Google Patents
Determination method and device for light source position and electronic equipment Download PDFInfo
- Publication number
- CN110598333B CN110598333B CN201910875146.3A CN201910875146A CN110598333B CN 110598333 B CN110598333 B CN 110598333B CN 201910875146 A CN201910875146 A CN 201910875146A CN 110598333 B CN110598333 B CN 110598333B
- Authority
- CN
- China
- Prior art keywords
- furniture
- house
- information
- light source
- determining
- 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
Images
Landscapes
- Image Analysis (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for determining the position of a light source and electronic equipment, which relate to the technical field of decoration design and comprise the following steps: acquiring house information of a target house; determining a target house type diagram of a target house based on house information; the target house type graph comprises one or more of furniture position information, furniture height information and furniture shape and size information; and determining the light source position of the target house based on the deep learning algorithm and the target house pattern. The invention improves the calculation efficiency of determining the position of the light source.
Description
Technical Field
The present invention relates to the field of decoration design technologies, and in particular, to a method and an apparatus for determining a light source position, and an electronic device.
Background
In modern house decoration, the light effect after finishing the decoration largely determines the quality of the whole design effect, and the influence of the visible light source plays a vital role in the whole decoration effect, so how to find the correct and proper light source position is very important. However, in the prior art, the light source position in the house type diagram is manually defined mostly, and the staff manually determines the position of the light source according to the distance from the wall in the house type diagram, different space, furniture layout, distance between the light source and other dimension factors.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for determining the position of a light source and electronic equipment, so that the calculation efficiency for determining the position of the light source is improved.
In a first aspect, an embodiment of the present invention provides a method for determining a position of a light source, including: acquiring house information of a target house; determining a target house pattern diagram of the target house based on the house information; the target house type graph comprises one or more of furniture position information, furniture height information and furniture shape and size information; and determining the light source position of the target house based on a deep learning algorithm and the target house pattern.
In an alternative embodiment, the house information includes house profile and indoor layout information; the step of determining the target house type graph of the target house based on the house information comprises the following steps: determining furniture arrangement information of the target house based on the house outline and the indoor layout information, and determining furniture shape size and furniture position information of the target house according to the furniture arrangement information of the target house; determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height in the target house; and determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph.
In an optional embodiment, the step of determining the light source position in the target house type graph based on the deep learning algorithm and the target house type graph includes: inputting the target house type graph into a pre-trained DCGAN network model, and determining the light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on training of the light source positions of the known house type diagrams.
In an alternative embodiment, the method further comprises: and determining the light source coordinates of the target house type graph according to the center point of the light source position of the target house.
In a second aspect, an embodiment of the present invention provides a device for determining a position of a light source, including: the information acquisition module is used for acquiring house information of the target house; the house type diagram determining module is used for determining a target house type diagram of the target house based on the house information; the target house type graph comprises one or more of furniture position information, furniture height information and furniture shape and size information; and the light source position determining module is used for determining the light source position of the target house based on a deep learning algorithm and the target house pattern.
In an alternative embodiment, the house information includes house profile and indoor layout information; the house type diagram determining module is further used for determining furniture arrangement information of the target house based on the house outline and the indoor layout information, and determining furniture shape and size and furniture position information of the target house according to the furniture arrangement information of the target house; determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height in the target house; and determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph.
In an optional embodiment, the light source position determining module is further configured to input the target house type graph into a pre-trained DCGAN network model, and determine a light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on training of the light source positions of the known house type diagrams.
In an alternative embodiment, the apparatus further comprises: and the light source coordinate determining module is used for determining the light source coordinate of the target house type graph according to the central point of the light source position of the target house.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, and a processor, where the memory stores a computer program executable on the processor, where the processor implements the steps of the method according to the first aspect when the processor executes the computer program.
In a fourth aspect, embodiments of the present invention provide a computer readable medium storing computer executable instructions that, when invoked and executed by a processor, cause the processor to implement the method of the first aspect.
The embodiment of the invention provides a method and a device for determining the position of a light source and electronic equipment, wherein the method comprises the following steps: firstly, acquiring house information of a target house; then determining a target house pattern (comprising one or more of furniture position information, furniture height information and furniture shape and size information) of the target house based on the house information; and finally, determining the light source position of the target house based on the deep learning algorithm and the target house type graph. According to the method, on the basis of fully considering the light source position influence factors (furniture position information, furniture height information and furniture shape and size information), the light source position in the target house can be rapidly determined based on a deep learning algorithm and the target house type diagram of the target house, and the calculation efficiency of determining the light source position is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for determining a position of a light source according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for determining a position of a light source according to an embodiment of the present invention;
FIG. 3 is a schematic illustration of a house type provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of a two-dimensional target house type provided by an embodiment of the present invention;
FIG. 5 is a schematic view of a house type with light source locations according to an embodiment of the present invention;
FIG. 6 is a house type diagram with light source coordinates according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a device for determining a position of a light source according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In consideration of the problem that the calculation efficiency is low due to the fact that the existing light source position determination technology has many factors, the embodiment of the invention provides a light source position determination method, a light source position determination device and electronic equipment, and the light source position determination method, the light source position determination device and the electronic equipment can be applied to determination of light source positions in house decoration design.
For the sake of understanding the present embodiment, a method for determining a position of a light source according to an embodiment of the present invention will be described in detail.
The embodiment of the invention provides a method for determining the position of a light source, referring to a flowchart of the method for determining the position of the light source shown in fig. 1, the method is executed by a controller of electronic equipment, and the method comprises the following steps of S102 to S106:
step S102: and acquiring house information of the target house.
The target house may be a house in which the position of the internal light source is required to be determined when the decoration design is performed. The house information is information that needs to be extracted from the target house when the light source position determination is performed, so as to determine the light source position based on the extracted house information. In one embodiment, house information may be obtained by identifying a house pattern of a target house, to obtain a complete house pattern scheme, and according to the obtained house pattern scheme data, the obtained house information includes: wall information, door and window information, outline information of a house pattern and the like, and obtaining indoor layout information in a house according to house information of the target house, wherein the indoor layout information comprises the following components: furniture position information, furniture height information, furniture shape and size information, and the like.
Step S104: determining a target house type diagram of a target house based on house information; the target floor plan includes one or more of furniture position information, furniture height information, and furniture shape and size information.
The target house type map may be a two-dimensional image capable of reflecting wall information, door and window information, outline information of the house type map, furniture position information, furniture height information, and furniture shape and size information of the target house. And drawing a target house pattern diagram of the target house based on the wall information, the door and window information, the outline information of the house pattern diagram and the indoor layout information in the house information.
Step S106: and determining the light source position of the target house based on the deep learning algorithm and the target house pattern.
The target house type diagram comprises wall information, door and window information, outline information of the house type diagram, furniture position information, furniture height information and furniture shape and size information of the target house, the light source position of the target house is determined based on a deep learning algorithm and the target house type diagram, influences of indoor furniture size and furniture placement position of a furniture altimeter on the light source position are fully considered according to actual scenes of the target house, a light source position result obtained based on the deep learning algorithm is more fit with the actual situation, and the rationality of light source position determination is improved.
According to the method for determining the light source position, provided by the embodiment of the invention, on the basis of fully considering the light source position influence factors (furniture position information, furniture height information and furniture shape and size information), the light source position in the target house can be rapidly determined based on the deep learning algorithm and the target house type diagram of the target house, so that the calculation efficiency of determining the light source position is improved.
The existing light source position determining technology does not consider furniture height information in the target house, so that the light effect of the determined light source position is poor, and the light source position determining method provided by the embodiment of the invention also considers furniture height in the target house, optimizes the light source position determining method and improves the accuracy of determining the light source position.
In order to improve the rationality of light source position determination, the embodiment provides a specific implementation manner of determining the house pattern diagram of the target house based on house information, wherein the house information comprises house outline and indoor layout information, and the specific implementation manner can be implemented with reference to the following steps (1) to (3):
step (1): and determining furniture arrangement information of the target house based on the house outline and the indoor layout information, and determining furniture shape and size and furniture position information of the target house according to the furniture arrangement information of the target house.
The furniture arrangement information can also be obtained based on a house pattern of the target house, the furniture arrangement information comprises the arrangement position of each piece of furniture in the house, a top view of the piece of furniture and size information of the piece of furniture, the arrangement position can be the relative position relation between the piece of furniture in the house and the wall body outline, and the shape, size and position information of the piece of furniture in the target house can be determined based on the house outline and the indoor layout information in the house information.
Step (2): and determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height of the target house.
In one embodiment, the furniture image can also be determined from the top view of the piece of furniture and from the dimensional information of the piece of furniture. The shape of the furniture graph is determined according to the shape of the top view of the furniture, for example, the top view of the wardrobe and the bed is rectangular, the wardrobe and the bed are represented by rectangles with different sizes, and the size of the furniture can be reduced by a preset proportion according to the actual size of the furniture, so that the size of the furniture graph is obtained. In order to convert three-dimensional information (e.g., the height of furniture) in a target house into two-dimensional information, the color depth of a furniture pattern may be determined according to the height of furniture in the target house, so that the furniture height information is represented by furniture patterns of different shades, for example, a relationship table of the color depth of the furniture pattern and the height of furniture may be established, and the height of furniture may be determined according to the relationship table and the color of the furniture pattern.
In another embodiment, according to the top view of all pieces of furniture and according to the position information of the pieces of furniture, the maximized rectangle is drawn to just surround all parts of the furniture, so that each piece of furniture can be represented by a rectangular block, and as the specific furniture outline and furniture texture have small influence on the calculation of the light source position, pieces of furniture in the target house can be determined as rectangular blocks with different sizes, the aspect ratio of the rectangular blocks can be determined according to the aspect ratio of the actual size of the furniture, and the aspect ratio of the rectangular blocks of different pieces of furniture is different.
Step (3): and determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph.
In order to make the calculated light source position more accurate, the target house type graph can contain more influencing factors influencing the light source position, for example, furniture in the target house has a great influence on lamplight, including the size, placement and height of the furniture, and the target house type graph of the target house is determined according to the furniture position information, the furniture graph and the color depth of the furniture graph, so that the house type graph includes the furniture position information, the furniture height information and the furniture shape and size information.
In order to improve the accuracy of light source position determination, the embodiment provides a specific implementation manner of determining the light source position in the target house type diagram based on a deep learning algorithm and the target house type diagram: inputting the target house type graph into a pre-trained DCGAN (Deep Convolution Generative Adversarial Networks) network model, generating an countermeasure network by deep convolution, and determining the light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on a known house type graph and light source position training of the known house type graph. Firstly, training the DCGAN network model by using a known house type graph and the light source position of the known house type graph, wherein the known house type graph comprises wall information, door and window information, outline information of the house type graph, furniture position information, furniture height information and furniture shape and size information in the known house type, inputting the light source positions of the known house type graph and the known house type graph into the DCGAN network model, and training the DCGAN network model to enable the DCGAN network model to learn the mapping relation between the information of the known house type graph (comprising the wall information, the door and window information, the outline information of the house type graph, the furniture position information, the furniture height information and the furniture shape and size information) and the light source position of the known house type graph. The target house type diagram is input into a trained DCGAN network model, and the trained DCGAN network model can determine the optimal light source position in the target house according to wall information, door and window information, outline information of the house type diagram, furniture position information, furniture height information and furniture shape and size information in the target house type diagram. The DCGAN network model obtains the light source position of the target house type graph in a backtracking mode based on the existing high-quality rendering scheme effect graph. The light source position may be output as the vertex coordinate position of the pixel region, or may be output by drawing the pixel region of the light source position on the target floor plan.
The DCGAN network model is a combination of CNN (Convolutional Neural Networks, convolutional neural network) and GAN (Generative Adversarial Networks, generating type countermeasure network), which introduces the convolutional network into the generating type model to perform unsupervised training, and utilizes the strong feature extraction capability of the convolutional network to improve the learning effect of the generating network. In one embodiment, the DCGAN network model in the present application adopts a GAN in a base version, where two opposite networks G and D are used in the GAN, G is a generating network, D is a discriminating network, the purpose of G is to generate an image through network parameters, D is to determine true and false of the image, the two networks are mutually opposed, the more true the image generated by the G is, the higher the probability of judging errors by the D is, and because a trained group is provided, the capability of the D can be continuously improved, and in turn, the capability of the G to generate a higher quality image can be continuously promoted, so that in the continuous mutual opposed promotion, the G can completely generate data which is almost close to a real image, and the main purpose is to better extract the characteristics of a target household pattern graph by introducing a convolutional neural network CNN. Therefore, by combining the base-GAN with the CNN, the generating network is continuously optimized, so that the DCGAN network model generates a house pattern diagram with a proper light source position.
In order to improve user experience and make the light source position more intuitive, the method for determining the light source position provided in this embodiment further includes: and determining the light source coordinates of the target house type graph according to the center point of the light source position of the target house. The calculated light source positions are a plurality of pixel matrixes at specific positions in the target house type graph, the pixel values around the pixel matrixes are 0, so that the accuracy of the calculated light source positions is improved, the specific installation position of the later-stage lamp is conveniently determined, and the center point of each light source position pixel matrix is calculated to be used as the light source coordinate of the target house type graph. According to the light source coordinates in the house type graph, the light source coordinates can be applied to the decoration design graph, and according to the light source coordinate positions, a light source is added to the light source positions in the 3D graph of the house, and a complete house decoration design effect graph is displayed through rendering of the light source.
In practical applications, referring to the flowchart of the method for determining the position of the light source shown in fig. 2, the method for determining the position of the light source can be used to generate the position of the light source in the house type map, and specifically, the method can be executed with reference to the following steps S202 to S208:
step S202: and acquiring a two-dimensional target house pattern diagram of the target house according to house information of the target house.
Specifically, all wall body and furniture information of the target house can be obtained by identifying the house type diagram of the target house, or the wall body information of the target house is drawn according to the analysis file of the existing house type diagram to obtain a complete outline diagram with house structure layout; drawing furniture in the target house in the profile diagram, according to the top view of all furniture and according to the specific positions of the furniture, taking the maximum just surrounding all parts of the furniture as a standard, using rectangular blocks to represent and replace all furniture, abstracting all furniture information, and omitting the detail information because the specific furniture profile and texture have smaller influence on the light source position; although the detail features of the furniture can be abstracted, the furniture height has a great influence on the determination of the position of the light source, so that the heights of all furniture are converted into gray rectangular blocks with different shades to be represented, the darker the color of the rectangular blocks is, the higher the height of the furniture is represented, and in this way, the 3-dimensional furniture information can be converted into two-dimensional image information. Taking the house type diagram of the house A shown in fig. 3 as an example, by identifying the house type diagram of the house A, obtaining all wall and furniture information of the target house, and obtaining a two-dimensional target house type diagram of the house A according to furniture arrangement information and furniture size information of the house A, wherein the two-dimensional target house type diagram of the house A is shown in fig. 4.
Step S204: the DCGAN network model is trained using training images.
The training images are house type drawings and known light source positions in the house type drawings, wherein the house type drawings comprise wall information, door and window information, outline information, furniture position information, furniture height information and furniture shape and size information of houses. The specifications of the training images are unified, and a house type graph without a light source (also called a two-dimensional target house type graph) and a house type graph with a light source (the house type graph refers to a graph obtained through data drawing, data supplementing and data conversion) can be combined to form the training images; all training images may also be adjusted to the same size, e.g. 640 x 640 resolution.
Step S206: inputting the two-dimensional target house type graph into a pre-trained DCGAN network model, and generating the house type graph with the light source position based on the DCGAN network model.
Taking the two-dimensional target house type diagram of the house a shown in fig. 4 as an example, the two-dimensional target house type diagram of the house a is input into a trained DCGAN network model, the house type diagram with the light source position of the house a shown in fig. 5 is generated, and gray dots (other colors such as red) in fig. 5 are the generated light source positions.
Step S208: and determining the light source coordinates in the target house type graph based on the house type graph with the light source positions.
And extracting the light source position from the generated house type map with the light source position to obtain the house type map with the light source position, and comparing and dividing image pixels of the house type map with the light source position by adopting a threshold method according to the color channel to obtain all the light source positions. For example, when the generated light source positions are red dots, the furniture and the house outline are gray with different shades, the light source is red, and the contrast segmentation of the image pixel points is performed by adopting a threshold method, so that all the light source positions are obtained. The above-mentioned light source position is actually a pixel matrix at a specific position, and the coordinates of the light source, that is, the specific coordinates of the lighting, are determined by calculating the center point of the light source position. Taking the house type diagram with the light source position of the house A shown in fig. 5 as an example, comparing and dividing the image pixel points by a threshold method to obtain all the light source positions in fig. 5, and calculating the center point of the light source positions to obtain the house type diagram with the light source coordinates of the house A, such as the house type diagram with the light source coordinates shown in fig. 6.
According to the method for determining the light source position, three-dimensional information in house information is converted into the two-dimensional target house type graph, influences of furniture size, height and placement positions in the target house on the light source position are fully considered, the DCGAN network model obtained through training and the light source position result obtained according to the DCGAN network model are more attached to the actual condition of the target house, and the rationality and accuracy of light source position determination are improved.
Corresponding to the above method for determining the position of the light source, an embodiment of the present invention provides a device for determining the position of the light source, referring to a schematic structure diagram of the device for determining the position of the light source shown in fig. 7, including:
an information acquisition module 71 for acquiring house information of the target house.
A family pattern determining module 72 for determining a target family pattern of the target house based on the house information; the target floor plan includes one or more of furniture position information, furniture height information, and furniture shape and size information.
The light source position determining module 73 is configured to determine a light source position of the target house based on the deep learning algorithm and the target house pattern.
According to the light source position determining device provided by the embodiment, on the basis of fully considering the light effect influencing factors (furniture position information, furniture height information and furniture shape and size information), the light source position in the target house can be rapidly determined based on the deep learning algorithm and the target house type diagram of the target house, and the calculation efficiency of determining the light source position is improved.
In one embodiment, the house information includes house profile and indoor layout information; the above-mentioned house pattern determining module 72 is further configured to determine furniture arrangement information of the target house based on the house contour and the indoor layout information, and determine furniture shape size and furniture position information of the target house according to the furniture arrangement information of the target house; determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height in the target house; and determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph.
In one embodiment, the light source position determining module 73 is further configured to input the target house pattern into a pre-trained DCGAN network model, and determine the light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on a known house type graph and light source position training of the known house type graph.
In one embodiment, the apparatus further comprises:
and the light source coordinate determining module is used for determining the light source coordinate of the target house type graph according to the central point of the light source position of the target house.
According to the light source position determining device provided by the embodiment, the three-dimensional information in the house information is converted into the two-dimensional target house type graph, the influence of furniture size, height and placement position in the target house on the light source position is fully considered, the DCGAN network model obtained through training and the light source position result obtained according to the DCGAN network model are more attached to the actual condition of the target house, and the rationality and accuracy of light source position determination are improved.
The device provided in this embodiment has the same implementation principle and technical effects as those of the foregoing embodiment, and for brevity, reference may be made to the corresponding content in the foregoing method embodiment for a part of the description of the device embodiment that is not mentioned.
An embodiment of the present invention provides an electronic device, as shown in a schematic structural diagram of an electronic device in fig. 8, where the electronic device includes a processor 81 and a memory 82, where the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the foregoing embodiment when executing the computer program.
Referring to fig. 8, the electronic device further includes: bus 84 and communication interface 83, processor 81, communication interface 83 and memory 82 are connected by bus 84. The processor 81 is arranged to execute executable modules, such as computer programs, stored in the memory 82.
The memory 82 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 83 (which may be wired or wireless), and may use the internet, a wide area network, a local network, a metropolitan area network, etc.
Bus 84 may be an ISA (Industry Standard Architecture ) bus, PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 8, but not only one bus or type of bus.
The memory 82 is configured to store a program, and the processor 81 executes the program after receiving an execution instruction, and a method executed by the apparatus for flow defining disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 81 or implemented by the processor 81.
The processor 81 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 81 or by instructions in the form of software. The processor 81 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), and the like. But may also be a digital signal processor (Digital Signal Processing, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA for short), 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 invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 82 and the processor 81 reads the information in the memory 82 and in combination with its hardware performs the steps of the method described above.
Embodiments of the present invention provide a computer readable medium storing computer executable instructions that, when invoked and executed by a processor, cause the processor to implement the methods described in the above embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. A method for determining a position of a light source, comprising:
acquiring house information of a target house;
determining a target house pattern diagram of the target house based on the house information; the target house type graph comprises one or more of furniture position information, furniture height information and furniture shape and size information;
determining the light source position of the target house based on a deep learning algorithm and the target house pattern;
the house information comprises house outline and indoor layout information;
the step of determining the target house type graph of the target house based on the house information comprises the following steps:
determining furniture arrangement information of the target house based on the house outline and the indoor layout information, and determining furniture shape size and furniture position information of the target house according to the furniture arrangement information of the target house;
determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height in the target house;
determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph;
the step of determining the light source position in the target house type graph based on the deep learning algorithm and the target house type graph comprises the following steps:
inputting the target house type graph into a pre-trained deep convolution to generate an antagonism network DCGAN network model, and determining the light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on training of the light source positions of the known house type diagrams.
2. The method according to claim 1, wherein the method further comprises:
and determining the light source coordinates of the target house type graph according to the center point of the light source position of the target house.
3. A light source position determining apparatus, comprising:
the information acquisition module is used for acquiring house information of the target house;
the house type diagram determining module is used for determining a target house type diagram of the target house based on the house information; the target house type graph comprises one or more of furniture position information, furniture height information and furniture shape and size information;
the light source position determining module is used for determining the light source position of the target house based on a deep learning algorithm and the target house pattern;
the house information comprises house outline and indoor layout information;
the house type diagram determining module is further used for determining furniture arrangement information of the target house based on the house outline and the indoor layout information, and determining furniture shape and size and furniture position information of the target house according to the furniture arrangement information of the target house; determining a furniture graph according to the furniture shape and the size of the target house, and determining the color depth of the furniture graph according to the furniture height in the target house; determining a target house type graph of the target house based on the furniture position information, the furniture graph and the color depth of the furniture graph;
the light source position determining module is further used for inputting the target house type graph into a pre-trained DCGAN network model, and determining the light source position of the target house based on the DCGAN network model; the DCGAN network model is obtained based on training of the light source positions of the known house type diagrams.
4. A device according to claim 3, characterized in that the device further comprises:
and the light source coordinate determining module is used for determining the light source coordinate of the target house type graph according to the central point of the light source position of the target house.
5. An electronic device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-2 when executing the computer program.
6. A computer readable medium, characterized in that it stores computer executable instructions that, when invoked and executed by a processor, cause the processor to implement the method of any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910875146.3A CN110598333B (en) | 2019-09-16 | 2019-09-16 | Determination method and device for light source position and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910875146.3A CN110598333B (en) | 2019-09-16 | 2019-09-16 | Determination method and device for light source position and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110598333A CN110598333A (en) | 2019-12-20 |
| CN110598333B true CN110598333B (en) | 2023-05-16 |
Family
ID=68860331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910875146.3A Active CN110598333B (en) | 2019-09-16 | 2019-09-16 | Determination method and device for light source position and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598333B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402409B (en) * | 2020-04-03 | 2021-03-05 | 湖北工业大学 | Exhibition hall design illumination condition model system |
| CN112257131B (en) * | 2020-09-18 | 2023-10-03 | 杭州群核信息技术有限公司 | Method for realizing suspended ceiling overlooking effect graph based on matrix transformation |
| CN112257272B (en) * | 2020-10-26 | 2024-01-23 | 南京国豪家装饰设计有限公司 | Decoration design method of furniture set |
| CN118172476A (en) * | 2022-12-09 | 2024-06-11 | 华为技术有限公司 | Illumination estimation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778538A (en) * | 2012-10-17 | 2014-05-07 | 李兴斌 | Furniture simulation layout method and furniture simulation layout system |
| CN104778756A (en) * | 2015-04-10 | 2015-07-15 | 北京明兰网络科技有限公司 | Intelligent home decoration design system |
| CN109815641A (en) * | 2019-03-21 | 2019-05-28 | 河南工程学院 | DESIGN OF INTERI OR LIGHT method |
| 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 |
| CN110197225A (en) * | 2019-05-28 | 2019-09-03 | 广东三维家信息科技有限公司 | House type spatial match method and system based on deep learning |
| WO2019169699A1 (en) * | 2018-03-09 | 2019-09-12 | 平安科技（深圳）有限公司 | House model rendering method and apparatus, terminal device, and medium |
-
2019
- 2019-09-16 CN CN201910875146.3A patent/CN110598333B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778538A (en) * | 2012-10-17 | 2014-05-07 | 李兴斌 | Furniture simulation layout method and furniture simulation layout system |
| CN104778756A (en) * | 2015-04-10 | 2015-07-15 | 北京明兰网络科技有限公司 | Intelligent home decoration design system |
| WO2019169699A1 (en) * | 2018-03-09 | 2019-09-12 | 平安科技（深圳）有限公司 | House model rendering method and apparatus, terminal device, and medium |
| CN109815641A (en) * | 2019-03-21 | 2019-05-28 | 河南工程学院 | DESIGN OF INTERI OR LIGHT method |
| 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 |
| CN110197225A (en) * | 2019-05-28 | 2019-09-03 | 广东三维家信息科技有限公司 | House type spatial match method and system based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| Sonar-to-Satellite Translation using Deep Learning;Giovanni Giacomo等;《2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)》;20190117;全文 * |
| 室内图像中家具多标签标注的实现;马天瑶;《电脑知识与技术》;20180112;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110598333A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598333B (en) | Determination method and device for light source position and electronic equipment | |
| US10885660B2 (en) | Object detection method, device, system and storage medium | |
| US11127198B2 (en) | Graphics processing using directional representations of lighting at probe positions within a scene | |
| TW201740316A (en) | Image text identification method and apparatus | |
| US10204447B2 (en) | 2D image processing for extrusion into 3D objects | |
| CN112257328B (en) | Furniture layout method and electronic equipment | |
| US11182942B2 (en) | Map generation system and method for generating an accurate building shadow | |
| US9996961B2 (en) | Method and apparatus for generating a composite image based on an ambient occlusion | |
| CN110807807B (en) | Monocular vision target positioning pattern, method, device and equipment | |
| CN109348731A (en) | A kind of method and device of images match | |
| CN116524195B (en) | Semantic segmentation method, semantic segmentation device, electronic equipment and storage medium | |
| CN111738265A (en) | Semantic segmentation method, system, medium, and electronic device for RGB-D image | |
| JP2023505900A (en) | Methods and Related Apparatus for Occlusion Handling in Augmented Reality Applications Using Memory and Device Tracking | |
| US20140169684A1 (en) | Distance Metric for Image Comparison | |
| CN110929664A (en) | Image recognition method and device | |
| CN109978964A (en) | A kind of image formation method, device, storage medium and terminal device | |
| CN114387199A (en) | Image annotation method and device | |
| CN110751732B (en) | Method for converting 2D image into 3D image | |
| CN113658195B (en) | Image segmentation method and device and electronic equipment | |
| CN113343987B (en) | Text detection processing method and device, electronic equipment and storage medium | |
| CN116416290A (en) | Method and device for calculating speckle structure light depth and electronic equipment | |
| CN113538452A (en) | Furniture layout and three-dimensional visualization method, device and equipment | |
| TW202105320A (en) | Physical object image generation method and apparatus, and device | |
| CN109410224B (en) | Image segmentation method, system, device and storage medium | |
| CN117540043B (en) | Three-dimensional model retrieval method and system based on cross-instance and category comparison |
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 |