CN110211217B - Scene simulation type illumination light distribution method and device - Google Patents
Scene simulation type illumination light distribution method and device Download PDFInfo
- Publication number
- CN110211217B CN110211217B CN201910341571.4A CN201910341571A CN110211217B CN 110211217 B CN110211217 B CN 110211217B CN 201910341571 A CN201910341571 A CN 201910341571A CN 110211217 B CN110211217 B CN 110211217B
- Authority
- CN
- China
- Prior art keywords
- light
- distribution
- hyperspectral
- light distribution
- semantic
- 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 50
- 238000005286 illumination Methods 0.000 title claims abstract description 33
- 238000004088 simulation Methods 0.000 title claims abstract description 27
- 239000000126 substance Substances 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 75
- 230000009466 transformation Effects 0.000 claims description 49
- 238000012937 correction Methods 0.000 claims description 17
- 238000013461 design Methods 0.000 description 17
- 230000003595 spectral effect Effects 0.000 description 11
- 238000001228 spectrum Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 230000008447 perception Effects 0.000 description 6
- 239000002131 composite material Substances 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 5
- 238000011176 pooling Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001678 irradiating effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/50—Lighting effects
- G06T15/506—Illumination models
Abstract
The application provides a scene simulation type illumination light distribution method and device, wherein the method comprises the following steps: step 1: determining a semantic scene corresponding to the light distribution of the product; step 2: invoking a light distribution scheme corresponding to the semantic scene from a semantic model library; the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source; step 3: and carrying out light distribution on the product according to the light distribution scheme. According to the invention, the required light distribution scheme is called from the preset semantic model library, so that the light distribution setting of the required scene can be completed quickly and efficiently, and the light distribution designer is not required to complete the light distribution setting of the required scene, thereby improving the light distribution efficiency and stability and reducing the light distribution cost.
Description
Technical Field
The invention relates to the technical field of light processing, in particular to a scene simulation type illumination light distribution method and device.
Background
The light distribution design is a skill for showing commodity charm by combining various props with aesthetic and professional skills, and is an important mode of visual marketing. The light distribution designer needs to grasp various skills including aesthetic ability, commercial ability, professional skills, and the like. In the light distribution design, the lighting design is a part of importance, and the lighting not only provides a light source, but also plays roles of creating atmosphere, highlighting products and the like. The selection of the light is very important to the display of the product in the light distribution design. The absorption and reflection of different light by an object are distributed differently, and the spectrum in nature is quite diverse, so that the colors exhibited by the object under different ambient lights are different. For example, in the light distribution of fruit areas in supermarkets, it is desirable to achieve a vivid and tender fruit color, so that different lights may be required to illuminate different colors of fruit. The selection of proper light in the traditional light distribution design often requires abundant experience and deep expertise of a light distribution designer, and the situation causes high labor cost of the light distribution design, and has higher aesthetic requirements and instability of the design effect in the personal design. Because the light distribution design is used for marketing the commodity, the instability of the illumination design can lead to greater loss of commercial value.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a scene simulation type illumination light distribution method and device with stable light distribution effect and low light distribution cost.
The invention adopts the following technical scheme:
a scene simulation type illumination light distribution method comprises the following steps:
step 1: determining a semantic scene corresponding to the light distribution of the product;
step 2: invoking a light distribution scheme corresponding to the semantic scene from a semantic model library;
the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source;
step 3: and carrying out light distribution on the product according to the light distribution scheme.
Further, according to the scene simulation type illumination light distribution method, the semantic model library also comprises reference standard hyperspectral distribution information, wherein the reference standard hyperspectral distribution information is hyperspectral distribution information of a standard substance under white light; the step 2 comprises the following steps:
step 2.1: obtaining hyperspectral distribution information of a product under white light;
step 2.2: comparing the hyperspectral distribution information with the reference standard hyperspectral distribution information to obtain a difference relation;
step 2.3: and correcting the light distribution scheme according to the difference relation.
Further, according to the scene simulation type illumination light distribution method, the standard substance is a white board.
Further, in the scene simulation illumination distribution method, step 2.3 includes:
obtaining a transformation matrix according to the difference relation, and then correcting the formula scheme according to the transformation matrix; wherein the transformation matrix is constructed using a light intensity matrix.
Further, as described above, the method for correcting in step 2.3 is as follows:
multiplying the transformation matrix with the light intensity matrix to obtain the corrected light source light intensity parameter.
A scene simulation type illumination light distribution device, comprising:
the confirming module is used for confirming a semantic scene corresponding to the light distribution of the product;
the invoking module is used for invoking the light distribution scheme corresponding to the semantic scene from the semantic model library; the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source;
and the light distribution module is used for distributing light to the product according to the light distribution scheme.
Further, as described above, the semantic model library further includes reference standard hyperspectral distribution information, where the reference standard hyperspectral distribution information is hyperspectral distribution information of the standard product under white light; the calling module comprises:
the acquisition unit is used for acquiring hyperspectral distribution information of the product under white light;
a comparing unit for comparing the hyperspectral distribution information with the reference standard hyperspectral distribution information to obtain a difference relation;
and the correction unit is used for correcting the light distribution scheme according to the difference relation.
Further, in the scene simulation type illumination light distribution device, the standard substance is a white board.
Further, as described above, the correction unit is further configured to obtain a transformation matrix according to the difference relationship, and then correct the light distribution scheme according to the transformation matrix; wherein the transformation matrix is constructed using a light intensity matrix.
Further, in the scene simulation type illumination light distribution device, the correction unit is further configured to multiply the transformation matrix with the light intensity matrix to obtain the corrected light intensity parameter of the light source.
The beneficial effects are that:
according to the invention, the required light distribution scheme is called from the preset semantic model library, so that the light distribution setting of the required scene can be completed quickly and efficiently, and the light distribution designer is not required to complete the light distribution setting of the required scene, thereby improving the light distribution efficiency and stability and reducing the light distribution cost.
Drawings
FIG. 1 is a flow chart of a scene simulation type illumination light distribution method of the invention;
FIG. 2 is a block diagram of a scene simulation type illumination light distribution device;
FIG. 3 is a block diagram illustrating a call module according to the present invention;
FIG. 4 is a flow chart of a scene simulation type illumination distribution method in embodiment 1 of the invention;
FIG. 5 is a flow chart of a scene simulation type illumination distribution method in embodiment 2 of the present invention;
fig. 6 is a flowchart of a scene simulation type illumination distribution method according to embodiment 3 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the present invention will be clearly and completely described below, 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.
The method is to build a semantic model library of human perception of synthetic light. By setting different light intensities for some monochromatic lights, light synthesis is carried out, a composite light spectrum distribution curve synthesized under different combinations and semantic descriptions of human perception of the composite light, such as brightness, darkness, sunset, ocean and the like, are recorded in the model, and information of each single light intensity is recorded at the same time, so that a plurality of semantic scenes (such as brightness, darkness, sunset, ocean and the like) and a light distribution scheme corresponding to each semantic scene are stored in a semantic model library.
For example, the human perception semantic meaning of a complex light spectrum distribution curve S is "bright", and the complex light spectrum distribution curve S corresponds to the synthesized light composed of a single color light a with a light intensity parameter of 45%, a single color light B with a light intensity parameter of 10%, and a single color light C with a light intensity parameter of 15%; the light distribution scheme for storing the semantic scene bright in the semantic model library is as follows: the light intensity parameter of the lamp A is 45%; the light intensity parameter of the B lamp is 10%; the intensity parameter of the C lamp was 15%.
It can be understood that the specific method for establishing the semantic model library is not particularly limited, and can be established by adopting various methods, so long as a plurality of different semantic scenes are stored in the semantic model library, and a light distribution scheme corresponding to each semantic scene is stored.
Meanwhile, in some embodiments of the present invention, a spectrum response distribution obtained by irradiating a standard (such as a whiteboard) with white light is stored in the semantic model as a reference, and then compared with other products, so as to correct and adjust the light intensity parameter of each monochromatic light in the light distribution scheme. The hyperspectral camera and the white light source can be utilized to obtain the image information of the object, and the information is hyperspectral distribution information of the object.
The spectrum distribution curve of the compound-color light is respectively obtained according to red light,Relative spectral distribution function S of green light, blue light, and white light r (λ)、S g (λ)、S b (lambda) and S w (λ) the plotted image, where λ is the wavelength of light.
Through this semantic model described above, recommendations for each product to illuminate under a particular semantic scene can be obtained, including numerical recommendations for the light intensity of each product's light source. However, in a practical scenario, each product object has a different response to light, and simply applying the standardized light intensity ratio of the light source in the model may cause deviation of the final effect. To compensate for this, adjustments are required to the intensity data of each light source in the selected semantic scene in the model. The specific method for adjusting comprises the following steps: firstly, hyperspectral distribution of the product under white light is obtained and compared with hyperspectral distribution of a white light irradiation standard substance in a model to obtain a difference relation, and the response difference of the product and the standard substance to light can be determined through the difference relation, so that the light intensity data of each light source in a semantic scene selected in the model can be adjusted according to the response difference.
Of course, it can be understood that the specific adjustment method may be various, for example, the hyperspectral distribution information acquired by using the hyperspectral camera may be finely adjusted by a certain calculation method according to the difference relationship, the fine adjustment standard is a transformation matrix S, and the light intensity of each monochromatic light in a certain semantic scene in the semantic model is corrected by the transformation matrix S. It will be appreciated that the fine tuning criteria may be derived by simple mathematical techniques, or by using neural networks or other methods, or even not necessarily a matrix, but other means of representing the change, to obtain the light intensity parameters of the light source for the desired article in a particular situation.
Fig. 1 is a flowchart of a scene simulation type illumination light distribution method according to the present invention, and as shown in fig. 1, the scene simulation type illumination light distribution method provided by the present invention includes the following steps:
step 1: determining a semantic scene corresponding to the light distribution of the product;
the semantic scene is a semantic description of a multi-colored light perception, such as bright, dim, sunset, ocean, etc. The light distribution scheme is a set of parameter information formed by corresponding light source light intensity parameters under a certain semantic scene. The light intensity parameters of the light source are light intensity information corresponding to the light lights with different colors. For example, the light distribution scheme may be: (sunset: 35% lamp A, 12% lamp B, 7% lamp C);
step 2: invoking a light distribution scheme corresponding to the semantic scene from a semantic model library;
specifically, the semantic model library consists of different semantic scenes and a light distribution scheme under each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source. The semantic model library is established by human perception of composite light, and by setting different light intensities for some monochromatic lights, light synthesis is carried out, a composite light spectrum distribution curve synthesized under different combinations is recorded in the semantic model library, and semantic descriptions of human perception of the composite light, such as brightness, darkness, sunset, ocean and the like, are recorded, and meanwhile, information of each monochromatic light intensity is recorded, so that the semantic model library is formed. Illustrating: the light distribution scheme comprises the following parameter information: the light intensity parameters corresponding to the brightness are: the light intensity parameter of the lamp A is 45%; the light intensity parameter of the B lamp is 10%; the intensity parameter of the C lamp was 15%.
Further, the step 2 specifically includes the following steps:
step 2.1: obtaining hyperspectral distribution information of a product under white light;
and taking a photo of the product to be subjected to light distribution under the white light by using a hyperspectral camera, and obtaining hyperspectral distribution information of the product under the white light by the taken photo.
Step 2.2: comparing the hyperspectral distribution information with reference standard hyperspectral distribution information to obtain a difference relation;
the semantic model library also comprises reference standard hyperspectral distribution information, wherein the reference standard hyperspectral distribution information is hyperspectral distribution information of a standard substance under white light; the reference standard hyperspectral distribution information is hyperspectral distribution information obtained by irradiating white light to a certain standard substance; the hyperspectral distribution information obtained by the pictures shot by the hyperspectral cameras is compared with the reference standard hyperspectral distribution information to obtain a difference relation, the difference relation and the hyperspectral distribution information obtained by the hyperspectral cameras are subjected to fine adjustment through a certain calculation method, the fine adjustment standard is a transformation matrix S, the fine adjustment standard can be deduced through simple mathematics, other methods such as a neural network and the like can be utilized, even a matrix is not necessarily used, but other modes representing changes (as long as the hyperspectral pictures are utilized for carrying out light distribution assistance, the light distribution scheme under a required scene is finally obtained, and the light distribution scheme is within the protection scope of the application), so that the light source intensity parameter of a required object under a certain specific condition is obtained, and the following steps are specifically referred to.
Step 2.3: and correcting the hyperspectral distribution information according to the difference relation, so as to obtain corrected light source light intensity parameters, and further determining a light distribution scheme of the sample requiring light distribution in the current scene.
In a specific embodiment of the present invention, a transformation matrix is used to perform auxiliary light distribution on the hyperspectral image, and in this embodiment, the comparing method in step 2.3 specifically includes:
obtaining a transformation matrix S according to the difference relation, and correcting the hyperspectral distribution information according to the transformation matrix S so as to obtain corrected light source light intensity parameters; wherein, the transformation matrix S is:
k is the number of wave numbers σ, k=0, 1,2, 3..k-1, where 0.ltoreq.k.ltoreq.n/2; n is 512 or 1024, and the transformation matrix is constructed by using an optical intensity matrix I, where the optical intensity matrix I is:
where N is 512 or 1024.
The method of correction in step 2.3 is as follows:
multiplying the transformation matrix S with the light intensity matrix I to obtain a corrected light intensity parameter of the light source;
B＝S·I
wherein,
b (σ (k)) is the spectral intensity of wavenumber σ (k), wavenumber σ (k) =σmin+kδσ, σmin is the recovered minimum wavenumber, and δσ is the spectral resolution.
Step 3: and carrying out light distribution on the product according to the light distribution scheme.
Because the design of the lamplight in the traditional light distribution design depends on a large amount of experience, the final effect is unstable, the risk is high, and the cost is high, the semantic scene lamplight standard proportion is adjusted by utilizing the semantic model library and through the difference of hyperspectral distribution of the actual product and the standard product, and the requirements of different lighting effects on different products in the light distribution design are realized. Compared with the traditional method, the efficiency and the accuracy are improved. And because the light sources in the library are determined, the intensity of each light source is only required to be adjusted when the proportioning is recommended, and the light sources are not required to be temporarily searched when the light source is actually used, the cost is reduced, and the operation stability is improved.
It is understood that the standard in the semantic model library is mainly used as a reference for correcting and adjusting the light distribution scheme, so the invention is not particularly limited to the standard, and various articles can be adopted. In some embodiments of the present invention, the standard is a white board, and the light distribution scheme can be more accurately and finely adjusted through the reference standard hyperspectral distribution information obtained by the white board under the irradiation of white light.
As shown in fig. 3, another object of the present invention is to further provide a scene simulation type illumination light distribution device, which includes:
the confirming module is used for confirming a semantic scene corresponding to the light distribution of the product;
the invoking module is used for invoking the light distribution scheme corresponding to the semantic scene from the semantic model library; the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source;
and the light distribution module is used for distributing light to the product according to the light distribution scheme.
As shown in fig. 4, the semantic model library further includes reference standard hyperspectral distribution information, where the reference standard hyperspectral distribution information is hyperspectral distribution information of the standard product under white light; the calling module comprises:
the acquisition unit is used for acquiring hyperspectral distribution information of the product under white light;
a comparing unit for comparing the hyperspectral distribution information with the reference standard hyperspectral distribution information to obtain a difference relation;
and the correction unit is used for correcting the light distribution scheme according to the difference relation.
The correction unit is also used for obtaining a transformation matrix S according to the difference relation, and then correcting the hyperspectral distribution information according to the transformation matrix S so as to obtain corrected light source light intensity parameters; wherein a transformation matrix is obtained, which is constructed using the light intensity matrix I. For example, in a specific embodiment of the present invention, the transformation matrix S is:
k is the number of wave numbers σ, k=0, 1,2, 3..k-1, where 0.ltoreq.k.ltoreq.n/2; n is 512 or 1024, and the transformation matrix is constructed by using an optical intensity matrix I, where the optical intensity matrix I is:
where N is 512 or 1024.
In a specific embodiment of the present invention, the correction unit is further configured to multiply the transformation matrix S with the light intensity matrix I to obtain a corrected light intensity parameter of the light source;
B＝S·I
wherein,
b (σ (k)) is the spectral intensity of wavenumber σ (k), wavenumber σ (k) =σmin+kδσ, σmin is the recovered minimum wavenumber, and δσ is the spectral resolution.
The following three embodiments respectively describe the illumination light distribution method based on the scene simulation.
The light distribution method can be used for assisting indoor light distribution design, and recommendation of different light combinations is provided for different commodities in indoor display according to a user requirement scene. For example, when fruits in supermarkets are displayed, fruits are required to be bright and beautiful in color under the light, and the recommendation can be made for the light ratio according to the requirements. In the display of articles in a showcase of a museum, or in the display of products in a market, the display of works of art such as indoor and outdoor sculpture and the like, the method can make recommendation of light matching according to the effect required in the scene.
The light distribution scheme of the present invention will be specifically described below by way of two examples.
Example 1:
the embodiment provides a scene for showing articles in a shop window of a museum, wherein the illumination scene required by the articles is sunset, as shown in fig. 4, the spectrum scene simulation type illumination light distribution method comprises the following steps:
step 1: determining a semantic scene corresponding to the light distribution of the article as a sunset;
step 2: the light distribution scheme corresponding to the sunset is called from the semantic model library as follows: the semantic scene is sunset, and the light source intensity parameters corresponding to the sunset are as follows: the light intensity parameter of the lamp A is 35%; the light intensity parameter of the B lamp is 12%; the light intensity parameter of the C lamp is 7%; taking a picture of an article in a shop window of a museum under white light by using a hyperspectral camera to obtain hyperspectral distribution information of the article under white light;
step 3: comparing the hyperspectral distribution information obtained in the step 2 with reference standard hyperspectral distribution information to obtain a transformation matrix; the reference standard hyperspectral distribution information is hyperspectral distribution information obtained by a white board shot by a hyperspectral camera under white light;
step 4: correcting the light source light intensity parameters (35% of the light intensity parameters of the A lamp, 12% of the light intensity parameters of the B lamp and 7% of the light intensity parameters of the C lamp) in the step 1 by utilizing the transformation matrix, and finally adjusting the light source light intensity parameters from (35% of the light intensity parameters of the A lamp, 12% of the light intensity parameters of the B lamp and 7% of the light intensity parameters of the C lamp) to (40% of the light intensity parameters of the A lamp, 10% of the light intensity parameters of the B lamp and 5% of the light intensity parameters of the C lamp) according to the correction method;
the specific correction method comprises the following steps: obtaining corrected light source light intensity parameters (40% of the light intensity parameters of the A lamp, 10% of the light intensity parameters of the B lamp and 5% of the light intensity parameters of the C lamp) by multiplying the transformation matrix S with the light intensity matrix I;
wherein, the transformation matrix S is:
k is the number of wave numbers σ, k=0, 1,2, 3..k-1, where 0.ltoreq.k.ltoreq.n/2, where k=4, N is 512, the transformation matrix is constructed using a light intensity matrix I, which is:
wherein N is 512.
Multiplying the transformation matrix S with the light intensity matrix I to obtain a corrected light intensity parameter of the light source;
B＝S·I
wherein,
b (σ (k)) is the spectral intensity of wavenumber σ (k), wavenumber σ (k) =σmin+kδσ, σmin is the recovered minimum wavenumber, and δσ is the spectral resolution.
Step 5: and (3) re-dimming the lamplight of the shop window of the museum by using the corrected light source light intensity parameters (40% of the light intensity parameters of the lamp A, 10% of the light intensity parameters of the lamp B and 5% of the light intensity parameters of the lamp C), so as to obtain the optimal lamplight setting under the scene.
Example 2:
the embodiment provides a scene for showing articles in a supermarket, wherein the illumination scene required by the articles is warm, as shown in fig. 5, the spectrum scene simulation type illumination light distribution method comprises the following steps:
step 1: determining the semantic scene of the object light distribution as warm;
step 2: the light distribution scheme corresponding to warmth is called from the semantic model as follows: the semantic scene is warm, and the light intensity parameters of the light source corresponding to the warm are as follows: the light intensity parameter of the lamp A is 45%; the light intensity parameter of the B lamp is 20%; the light intensity parameter of the C lamp is 6%; taking a photo of the object under white light by using a hyperspectral camera to obtain hyperspectral distribution information of the object under white light;
step 3: comparing the hyperspectral distribution information obtained in the step 2 with reference standard hyperspectral distribution information to obtain a transformation matrix; the reference standard hyperspectral distribution information is hyperspectral distribution information obtained by a white board shot by a hyperspectral camera under white light;
step 4: correcting the light source light intensity parameters (45% of the light intensity parameters of the A lamp, 20% of the light intensity parameters of the B lamp and 6% of the light intensity parameters of the C lamp) in the step 1 by utilizing the transformation matrix, and finally adjusting the light source light intensity parameters from (45% of the light intensity parameters of the A lamp, 20% of the light intensity parameters of the B lamp and 6% of the light intensity parameters of the C lamp) to (30% of the light intensity parameters of the A lamp, 15% of the light intensity parameters of the B lamp and 8% of the light intensity parameters of the C lamp) according to the correction method;
the specific correction method comprises the following steps: obtaining corrected light source light intensity parameters (30% of the light intensity parameters of the A lamp, 15% of the light intensity parameters of the B lamp and 8% of the light intensity parameters of the C lamp) by multiplying the transformation matrix S with the light intensity matrix I;
wherein, the transformation matrix S is:
k is the number of wave numbers σ, k=0, 1,2, 3..k-1, where 0.ltoreq.k.ltoreq.n/2,K =7, N is 1024, the transformation matrix is constructed using an intensity matrix I, which is:
where N is 1024.
Multiplying the transformation matrix S with the light intensity matrix I to obtain a corrected light intensity parameter of the light source;
B＝S·I
wherein,
b (σ (k)) is the spectral intensity of wavenumber σ (k), wavenumber σ (k) =σmin+kδσ, σmin is the recovered minimum wavenumber, and δσ is the spectral resolution.
Step 5: and (3) re-dimming the light of the supermarket by using the corrected light source light intensity parameters (30% of the light intensity parameters of the A lamp, 15% of the light intensity parameters of the B lamp and 8% of the light intensity parameters of the C lamp), so as to obtain the optimal light setting in the supermarket.
The light distribution method provided by the application can also be applied to the design of the front-mounted lamplight of the vehicle. When designing the front-end light (i.e. headlight) of the vehicle, the content of the indication board needs to be clear and not dazzling to human eyes when the indication board is illuminated by the light at night. The method provided by the application can make a recommendation for the headlight light ratio according to the effect requirement in the vehicle design, and the light distribution scheme of the invention is specifically described by the embodiment 3.
Example 3:
the embodiment provides a scene that is used for the sign place when driving at night in the region, needs the sign to show brightly after receiving vehicle light irradiation, as shown in fig. 6, and the grading method of vehicle light is:
step 1: the current scene is a night driving scene, so that the semantic scene corresponding to the area where the indication board is positioned is bright under the night driving scene;
step 2: the light distribution scheme corresponding to the brightness is called from the semantic model library as follows: the semantic scene is bright, and the light intensity parameters of the light source corresponding to the bright are as follows: the light intensity parameter of the lamp A is 50%; the light intensity parameter of the B lamp is 5%; the light intensity parameter of the C lamp is 14%; taking a photo of the indication board under white light by using a hyperspectral camera to obtain hyperspectral distribution information of the indication board under white light;
step 3: comparing the hyperspectral distribution information obtained in the step 2 with reference standard hyperspectral distribution information to obtain a transformation matrix; the reference standard hyperspectral distribution information is hyperspectral distribution information obtained by a white board shot by a hyperspectral camera under white light;
step 4: correcting the light source light intensity parameters (50% of the light intensity parameters of the A lamp, 5% of the light intensity parameters of the B lamp and 14% of the light intensity parameters of the C lamp) in the step 1 by utilizing the transformation matrix, and finally adjusting the light source light intensity parameters from (50% of the light intensity parameters of the A lamp, 5% of the light intensity parameters of the B lamp and 14% of the light intensity parameters of the C lamp) to (45% of the light intensity parameters of the A lamp, 10% of the light intensity parameters of the B lamp and 15% of the light intensity parameters of the C lamp) according to the correction method;
the specific correction method comprises the following steps: obtaining corrected light source light intensity parameters (45% of the light intensity parameters of the A lamp, 10% of the light intensity parameters of the B lamp and 15% of the light intensity parameters of the C lamp) by multiplying the transformation matrix S with the light intensity matrix I;
wherein, the transformation matrix S is:
k is the number of wave numbers σ, k=0, 1,2, 3..k-1, where 0.ltoreq.k.ltoreq.n/2,K = 5,N is 512, the transformation matrix is constructed using an intensity matrix I, which is:
where N is 1024.
Multiplying the transformation matrix S with the light intensity matrix I to obtain a corrected light intensity parameter of the light source;
B＝S·I
wherein,
b (σ (k)) is the spectral intensity of wavenumber σ (k), wavenumber σ (k) =σmin+kδσ, σmin is the recovered minimum wavenumber, and δσ is the spectral resolution.
Step 5: and (3) re-dimming the light of the area where the indication board driven at night is located by using the corrected light source light intensity parameters (45% of the light intensity parameters of the lamp A, 10% of the light intensity parameters of the lamp B and 15% of the light intensity parameters of the lamp C), so as to obtain the optimal light setting under the scene.
The following provides a light distribution method based on a neural network.
Example 4:
the embodiment provides a scene that is used for the sign place when driving at night in the region, needs the sign to show brightly after receiving vehicle light irradiation, then the grading method of vehicle light is:
step 1: determining that the current scene is a night driving, and then the light distribution scheme required by the area where the indication board is located under the night driving scene is as follows: the semantic scene is bright, and the light intensity parameters of the light source corresponding to the bright are as follows: the light intensity parameter of the lamp A is 50%; the light intensity parameter of the B lamp is 5%; the light intensity parameter of the C lamp is 14%;
step 2: taking a photo of the indication board under white light by using a hyperspectral camera to obtain hyperspectral distribution information of the indication board under white light;
step 3: adjusting the light distribution scheme by utilizing the hyperspectral distribution information by utilizing the constructed self-adaptive global pooling convolutional neural network;
the self-adaptive global pooling convolutional neural network is formed by sequentially connecting 1 input layer, 1 batch normalization layer, 6 hidden layers and one output layer; the first 4 hidden layers in the hidden layers each comprise convolution operation, activation operation, maximum pooling operation and local response normalization operation, the 5 th hidden layer comprises convolution and activation operation, and the 6 th hidden layer is global pooling operation;
step 4: correcting the light source light intensity parameters (50% of the light intensity parameters of the A lamp, 5% of the light intensity parameters of the B lamp and 14% of the light intensity parameters of the C lamp) in the step 1 by using the self-adaptive global pooling convolutional neural network, and finally adjusting the light source light intensity parameters (50% of the light intensity parameters of the A lamp, 5% of the light intensity parameters of the B lamp and 14% of the light intensity parameters of the C lamp) to (45% of the light intensity parameters of the A lamp, 10% of the light intensity parameters of the B lamp and 15% of the light intensity parameters of the C lamp) according to the correction method;
step 5: and (3) re-dimming the light of the area where the indication board driven at night is located by using the corrected light source light intensity parameters (45% of the light intensity parameters of the lamp A, 10% of the light intensity parameters of the lamp B and 15% of the light intensity parameters of the lamp C), so as to obtain the optimal light setting under the scene.
The scene simulation type illumination light distribution method and the corresponding device are not limited to indoor light distribution, and can also be outdoor light distribution, so long as the hyperspectral image is used for assisting in determining the design assistance of illumination light, and the scene simulation type illumination light distribution method and the corresponding device belong to the protection scope of the application.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; 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 technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. The scene simulation type illumination light distribution method is characterized by comprising the following steps of:
step 1: determining a semantic scene corresponding to the light distribution of the product;
step 2, calling a light distribution scheme corresponding to the semantic scene from a semantic model library;
the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source;
the semantic model library also comprises reference standard hyperspectral distribution information, wherein the reference standard hyperspectral distribution information is hyperspectral distribution information of a standard substance under white light, and the standard substance is a white board;
the step 2 comprises the following steps:
step 2.1: obtaining hyperspectral distribution information of a product under white light; taking a photo of a product to be subjected to light distribution under white light by using a hyperspectral camera, and acquiring hyperspectral distribution information of the product under white light by the taken photo;
step 2.2: comparing the hyperspectral distribution information with the reference standard hyperspectral distribution information to obtain a difference relation;
step 2.3, correcting the light distribution scheme according to the difference relation, namely obtaining a transformation matrix according to the difference relation, and correcting the light distribution scheme according to the transformation matrix;
wherein the transformation matrix is constructed using a light intensity matrix;
step 3: and carrying out light distribution on the product according to the light distribution scheme.
2. The scene modeling illumination distribution method according to claim 1, wherein the method of correction in step 2.3 is as follows:
multiplying the transformation matrix with the light intensity matrix to obtain the corrected light source light intensity parameter.
3. A scene simulation type illumination light distribution device, comprising:
the confirming module is used for confirming a semantic scene corresponding to the light distribution of the product;
the invoking module is used for invoking the light distribution scheme corresponding to the semantic scene from the semantic model library; the semantic model library comprises different semantic scenes and a light distribution scheme under each semantic scene; the light distribution scheme is a light source light intensity parameter corresponding to the standard substance in each semantic scene; the light source light intensity parameters comprise the types and the numbers of the monochromatic light sources and the light intensity of each monochromatic light source, wherein the standard substance is a whiteboard;
the light distribution module is used for distributing light to the product according to the light distribution scheme;
the semantic model library also comprises reference standard hyperspectral distribution information, wherein the reference standard hyperspectral distribution information is hyperspectral distribution information of a standard substance under white light; the calling module comprises:
the acquisition unit is used for acquiring hyperspectral distribution information of the product under white light; taking a photo of a product to be subjected to light distribution under white light by using a hyperspectral camera, and acquiring hyperspectral distribution information of the product under the white light by the taken photo;
a comparing unit for comparing the hyperspectral distribution information with the reference standard hyperspectral distribution information to obtain a difference relation;
and the correction unit is used for correcting the light distribution scheme according to the difference relation, in particular to obtain a transformation matrix according to the difference relation, and then correcting the light distribution scheme according to the transformation matrix, wherein the transformation matrix is constructed by utilizing a light intensity matrix.
The light distribution scheme comprises the step of obtaining hyperspectral distribution information of the product under white light.
4. A scene modeling illumination distribution device according to claim 3, wherein the correction unit is further configured to multiply the transformation matrix with the light intensity matrix to obtain the corrected light intensity parameter of the light source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910341571.4A CN110211217B (en) | 2019-04-25 | 2019-04-25 | Scene simulation type illumination light distribution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910341571.4A CN110211217B (en) | 2019-04-25 | 2019-04-25 | Scene simulation type illumination light distribution method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110211217A CN110211217A (en) | 2019-09-06 |
| CN110211217B true CN110211217B (en) | 2024-01-16 |
Family
ID=67786504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910341571.4A Active CN110211217B (en) | 2019-04-25 | 2019-04-25 | Scene simulation type illumination light distribution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110211217B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110740537B (en) * | 2019-09-30 | 2021-10-29 | 宁波燎原照明集团有限公司 | System for illumination system self-adaptive adjustment of museum cultural relics |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901134A (en) * | 2009-05-26 | 2010-12-01 | 耿英伟 | Guiding software for illuminating light distribution |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4437712B2 (en) * | 2004-07-07 | 2010-03-24 | 株式会社小糸製作所 | Vehicle lighting system |
| WO2015144209A1 (en) * | 2014-03-25 | 2015-10-01 | Metaio Gmbh | Method and system for representing a virtual object in a view of a real environment |
| US10375264B2 (en) * | 2016-04-28 | 2019-08-06 | University Of Southern California | Multispectral lighting reproduction |
-
2019
- 2019-04-25 CN CN201910341571.4A patent/CN110211217B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901134A (en) * | 2009-05-26 | 2010-12-01 | 耿英伟 | Guiding software for illuminating light distribution |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110211217A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101485234B (en) | Method of controlling a lighting system based on a target light distribution | |
| US10045417B2 (en) | Setting lighting based on the colors of samples | |
| US20190172415A1 (en) | Remote Color Matching Process and System | |
| CN1977542B (en) | Dominant color extraction using perceptual rules to produce ambient light derived from video content | |
| CN104360796B (en) | The method, apparatus and electronic equipment of color are applied on an electronic device | |
| RU2450476C2 (en) | Device and method to determine optimal backlighting | |
| CN110248450B (en) | Method and device for controlling light by combining people | |
| CN103761760B (en) | Method for manufacturing multi-view indoor design effect picture | |
| CN108182923A (en) | The method, display device and electronic equipment of image are shown on the display apparatus | |
| US9532021B2 (en) | True-color environment correction device and true-color environment correction method | |
| JP2009017354A (en) | Video signal processor, video display system, and video display processing method | |
| CN101383912B (en) | Color intelligent automatic regulating method for television video taking | |
| CN110211217B (en) | Scene simulation type illumination light distribution method and device | |
| CN106782367B (en) | Liquid crystal-spliced screen shows method and system | |
| CN108966449A (en) | A kind of lamp light control method | |
| US10959305B2 (en) | Controlling a lighting device having at least two electric light sources | |
| CN106102210A (en) | A kind of can the LED art work illuminator of Intelligent adjustment | |
| JP2018116771A (en) | Illumination apparatus | |
| Lin et al. | The study of a novel control method of the mood lighting emulator | |
| Catalbas et al. | Measurement of correlated color temperature from RGB images by deep regression model | |
| CN112188694A (en) | Lamplight color temperature correction method, system and device and storage medium | |
| CN111752506B (en) | Digital work display method, display device and computer readable medium | |
| CN113465742A (en) | Illumination optimization-based white light source illumination color resolution capability quantification method and system | |
| EP2452278A1 (en) | Method and apparatus for generating a sequence of a plurality of images | |
| Dai-yao | Visual Communication Design in Food Commercial Photography |
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 |