CN112989689A - Method for simulating RGB atmosphere light color - Google Patents
Method for simulating RGB atmosphere light color Download PDFInfo
- Publication number
- CN112989689A CN112989689A CN202110123140.8A CN202110123140A CN112989689A CN 112989689 A CN112989689 A CN 112989689A CN 202110123140 A CN202110123140 A CN 202110123140A CN 112989689 A CN112989689 A CN 112989689A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- rgb atmosphere
- training
- simulating
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000003062 neural network model Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 59
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 239000003086 colorant Substances 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 21
- 210000002569 neuron Anatomy 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 7
- 238000012360 testing method Methods 0.000 description 19
- 230000000694 effects Effects 0.000 description 12
- 239000011159 matrix material Substances 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000001746 injection moulding Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention discloses a method for simulating RGB atmosphere light color, which comprises the following steps: (1) constructing a neural network model, the neural network being constructed to: the input is R, G, B parameters, and the output is chromaticity coordinates x and y; (2) training sample data are collected based on an actual RGB atmosphere lamp; (3) preprocessing the training sample data; (4) training the neural network model by adopting the preprocessed training sample data until the training is finished; (5) preset R, G, B parameters are input into the trained neural network model, which outputs simulated chromaticity coordinates. The method can be free from the actual environment and the idle equipment, the RGB atmosphere light color can be adjusted and verified, the judgment work and the calibration steps of the lamp can be greatly simplified, the development efficiency of the lamp is effectively improved, and the method has very good popularization prospect and application value.
Description
Technical Field
The invention relates to a simulation method, in particular to a method for simulating light color.
Background
The light guide has the function of transmitting light, and in recent years, the light guide has been widely applied to the aspects of automobile interior lighting, atmosphere creation and the like, and has quite excellent implementation effect.
According to market demands, special color lights are often needed, and the special color lights can be blended by utilizing the existing color lights. It should be noted that the design of the light guide greatly affects the light mixing effect of various colors, such as light guide material, injection molding manner, structural design, etc., and these designs may cause the difference between the light emitting color and the theoretical color of the light guide of the luminaire to some extent. Therefore, the color of the RGB atmosphere lamp is one of the important indicators for lamp performance evaluation.
In the prior art, the requirements on the test environment are greatly limited for the work of judging and calibrating the light-emitting color and the like. Under the condition of no extra light and standard room temperature, a complete testing device is adopted, an atmosphere lamp testing rack is utilized to fix the lamp, and the chromatic value of the light-emitting surface is measured through a spectrometer. Only one set of colorimetric values can be obtained in each test, the operation is complex and time-consuming, and the heating of the LED caused by long-time operation can cause the problem of inaccurate measurement of subsequent colors.
Therefore, in the prior art, the technical scheme for judging the color of the RGB atmosphere lamp is complex, and the judgment result is very easily interfered by external factors. Due to the factors of environmental limitation, equipment limitation, complex operation and the like, the development work of the atmosphere lamp is difficult.
Based on this, aiming at the defects in the prior art, the invention is expected to obtain the method for simulating the RGB atmosphere lighting color, the method can simulate and identify the RGB atmosphere lighting color off line through the neural network, and the actual light-emitting color value can be obtained through the given input signal. The method can be free from the actual environment and the idle equipment, adjust and verify the atmosphere light color, greatly simplify the judgment work and the calibration steps of the lamp, and further effectively improve the development efficiency of the lamp.
Disclosure of Invention
One of the objectives of the present invention is to provide a method for simulating RGB atmosphere lighting colors, which can simulate the RGB atmosphere lighting colors through a neural network and identify the RGB atmosphere lighting colors offline, so that an actual color value of light output can be obtained by giving an input signal. The method can be free from the practical environment and the idle equipment, adjust and verify the atmosphere light color, and can greatly simplify the judgment work and the calibration steps of the lamp, thereby effectively improving the development efficiency of the lamp and having very good popularization prospect and application value.
In order to achieve the above object, the present invention provides a method for simulating RGB atmosphere lighting colors, comprising:
(1): constructing a neural network model, the neural network being constructed to: the input is R, G, B parameters, and the output is chromaticity coordinates x and y;
(2): training sample data are collected based on an actual RGB atmosphere lamp;
(3): preprocessing the training sample data;
(4): training the neural network model by adopting the preprocessed training sample data until the training is finished;
(5) preset R, G, B parameters are input into the trained neural network model, which outputs simulated chromaticity coordinates.
In the technical scheme of the invention, the neural network model for identifying the RGB atmosphere light colors can be constructed in Matlab simulation software. The method for identifying the RGB atmosphere light color by adopting the neural network can not be limited by a test place and equipment, and can finish the works of calibration, performance judgment and the like of the RGB atmosphere light color by only adopting computer simulation software, so that manpower and material resources can be effectively reduced, and the test cost is saved.
Further, in the method for simulating RGB atmosphere lighting colors according to the present invention, the neural network model is a BP neural network model.
Further, in the method for simulating RGB atmosphere light colors according to the present invention, the BP neural network model includes an input layer, a hidden layer, and an output layer, where the number of neurons in the hidden layer is 7.
Further, in the method for simulating RGB atmosphere lighting color, a sigmoid function is adopted as an activation function of the BP neural network model.
Further, in the method for simulating RGB atmosphere lighting colors according to the present invention, in step (2), different R, G, B are given for the actual RGB atmosphere lighting, the corresponding chromaticity coordinates x, y are obtained by actual measurement, and all the actually given R, G, B and the corresponding chromaticity coordinates x, y are used as training sample data.
Further, in the method for simulating RGB atmosphere lighting colors according to the present invention, in the step (3), the preprocessing includes a normalization processing.
Further, in the method for simulating the RGB atmosphere light color, the neural network model is trained by adopting a damped least square algorithm in the step (4).
Further, in the method for simulating RGB atmosphere lighting colors according to the present invention, in step (4), the objective function e (w) of the training process is:
in the above formula, YiRepresenting a target chromaticity value; y isi' denotes the actual chromaticity value of the RGB atmosphere lamp; p represents the number of training samples; w represents weight and threshold vectors; e.g. of the typei(w) denotes a chromaticity coordinate learning error, and i denotes an ith training sample.
Further, in the method for simulating RGB atmosphere lighting colors according to the present invention, in step (4), when the objective function is <0.0001, the training is completed.
Compared with the prior art, the method for simulating the RGB atmosphere light color has the following advantages and beneficial effects:
(1) the method for simulating the RGB atmosphere light color can simulate the RGB atmosphere light color and identify the RGB atmosphere light color off line by adopting the neural network, is not limited by a test place and equipment, can finish the works of calibration, performance judgment and the like of the RGB atmosphere light color only by adopting computer simulation software, can effectively reduce manpower and material resources, and saves the test cost.
(2) The method for simulating the RGB atmosphere light color is simple and convenient to operate, can effectively improve the development efficiency of the lamp, saves time and cost, greatly simplifies the judgment work and the calibration steps of the lamp, thereby effectively improving the development efficiency of the lamp, and has very good popularization prospect and application value.
(3) The method for simulating the RGB atmosphere light color can effectively avoid the error influence caused by overlong measuring time, and has higher accuracy.
(4) The method for simulating the RGB atmosphere light color has wide applicability, and not only can be suitable for lamps in the field of automobiles, but also can be suitable for various RGB atmosphere lamp lamps.
Drawings
Fig. 1 schematically shows a flow chart of a method for simulating RGB atmosphere lighting color according to the present invention, in an embodiment, a neural network model is used to identify RGB atmosphere lighting color.
Fig. 2 schematically shows a topology structure of a BP neural network model constructed by using the method for simulating RGB atmosphere lighting colors according to the present invention in one embodiment.
FIG. 3 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting color according to the present invention on the training set x value by using the neural network model in one embodiment.
FIG. 4 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting color according to the invention on the y value of the training set by using a neural network model in one embodiment.
FIG. 5 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting colors according to the invention on the test set x value by using a neural network model under one embodiment.
FIG. 6 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting colors according to the invention on the y value of the test set by using a neural network model in one embodiment.
Detailed Description
The method for simulating RGB atmosphere lighting colors according to the present invention will be further explained and illustrated with reference to the drawings and the specific embodiments of the specification, however, the explanation and the illustration do not limit the technical solution of the present invention to a proper way.
Fig. 1 schematically shows a flow chart of a method for simulating RGB atmosphere lighting color according to the present invention, in an embodiment, a neural network model is used to identify RGB atmosphere lighting color.
In the present invention, the method for simulating RGB atmosphere lighting colors according to the present invention may include:
(1) constructing a neural network model, the neural network being constructed to: the input is R, G, B parameters and the output is chromaticity coordinates x, y.
(2) Training sample data are collected based on actual RGB atmosphere lamps.
(3) And preprocessing the training sample data.
(4) And training the neural network model by adopting the preprocessed training sample data until the training is finished.
(5) Preset R, G, B parameters are input into the trained neural network model, which outputs simulated chromaticity coordinates.
As shown in fig. 1, in this embodiment, a BP neural network model for identifying RGB atmosphere light colors may be first constructed in Matlab simulation software, then weight values and threshold values in the BP neural network model are initialized, preprocessing including normalization processing is performed on training sample data, and the BP neural network model is trained by using the preprocessed training sample data.
In the training process of the BP neural network model, training sample data after normalization processing is input into the BP neural network model compiled by Matlab simulation software, the BP neural network model can be trained through continuous forward transmission and error reverse adjustment of a weight threshold value, and when an objective function E (w) <0.0001 is obtained, the training of the BP neural network model is completed.
In the step (1) of the method, the method can construct a neural network model for identifying RGB atmosphere light colors in Matlab simulation software. The method for identifying the RGB atmosphere light color by adopting the neural network can not be limited by a test place and equipment, and can finish the works of calibration, performance judgment and the like of the RGB atmosphere light color by only adopting computer simulation software, so that manpower and material resources can be effectively reduced, and the test cost is saved.
Correspondingly, in the method for simulating the RGB atmosphere light color, after the neural network model is constructed, the step (2) to the step (4) are further required to train the neural network model, so that the accuracy of the neural network model for identifying the RGB atmosphere light color is ensured.
It should be noted that, in step (2) of the method of the present invention, all the actually given R, G, B and its corresponding chromaticity coordinates x, y may be used as training sample data by giving different R, G, B to the actual RGB atmosphere lamps and actually measuring to obtain corresponding chromaticity coordinates x, y.
In this embodiment, taking a direct RGB atmosphere lamp as an example, an operator may input different R, G, B parameters, and then measure the light-emitting surface with a spectrometer to obtain corresponding chromaticity coordinates x and y, and then collect multiple sets of actually given R, G, B and their corresponding chromaticity coordinates x and y values that can be widely distributed on the chromatogram as training sample data.
After the training sample data is obtained, preprocessing operations including normalization processing need to be performed on the training sample data in step (3) of the method of the present invention. The normalization process is known in the art and will not be described herein.
Correspondingly, after the training sample data is preprocessed, in the step (4) of the method of the present invention, the constructed BP neural network model needs to be trained by using the preprocessed training sample data until the training is completed.
In this embodiment, a back propagation algorithm is adopted for training the BP neural network model, that is, after the input signal is transmitted in the forward direction to obtain the output of the BP neural network model, the error is back propagated, the previous layer is continuously processed, and the training is minimized through an objective function e (w).
In the process of training the BP neural network model, an objective function e (w) in the training process is:
in the above formula (1), YiRepresenting a target chromaticity value; y isi' denotes the actual chromaticity value of the RGB atmosphere lamp; p represents the number of training samples; w represents weight and threshold vectors; e.g. of the typei(w) denotes a chromaticity coordinate learning error, and i denotes an ith training sample.
Accordingly, in step (4) of the method of the present invention, the BP neural network model may be trained by using a damped least squares algorithm (levirberg Maquardt, LM), which may have both a local fast convergence property and a global search property.
In the damped least squares algorithm, the calculation formula of the weight threshold increment Δ w can be described as the following formula (2):
Δw＝[JT(w)J(w)+μI]-1JT(w)e(w) (2)
in the above formula (2), I represents an identity matrix; μ represents a defined learning rate; e (w) expressed as a chromaticity coordinate learning error; j (w) represents a Jacobian matrix; t denotes the transpose of the matrix.
The Jacobian matrix represented by j (w) can be expressed by the following formula (3):
in the above formula (3), e1(w)、eN(w) denotes a first chromaticity coordinate learning error and an Nth chromaticity coordinate learning error, respectively, w1、wnRespectively representing a first weight and threshold vector and an nth weight and threshold vector.
In training the neural network model, assume wkRepresenting the vector formed by the weight and the threshold of the kth iteration, the new vector formed by the weight and the threshold is wk+1The calculation can be performed by the following formula (4):
wk+1＝wk+Δw (4)
it can be seen that, with reference to the flowchart of the steps in fig. 1, in the embodiment shown in fig. 1, the calculating step of training the constructed BP neural network model by using the preprocessed training sample data in step (4) of the present invention may include the following steps S1-S6:
s1: setting in advance a training error value 0.0001 for error objective function, and initializing weight vector w (0), where k is 0 and μ is μ0。
S2: computing a neural network model output and an error objective function E (w)k)。
S3: calculating according to the formula (3) to obtain a Jacobian matrix J (w)k)。
S4: respectively calculating to obtain delta w and w according to the formulas (2), (4) and (1)k+1、E(wk+1)。
S5: if E (w)k+1)<E(wk) Go to subsequent step S6; otherwise, not updating the weight value, let wk+1＝wkAnd μ ═ μ × 10, the process returns to step S4 described above.
S6: judging whether the target function is less than 0.0001, and stopping the algorithm if the target function is less than 0.0001; otherwise, let k be k +1 and μ be μ/10, go back to S2.
Fig. 2 schematically shows a topology structure of a BP neural network model constructed by using the method for simulating RGB atmosphere lighting colors according to the present invention in one embodiment.
It should be noted that the principle of the light emission of the RGB atmosphere lamp is as follows: r, G, B three primary color signal values with the value range of [0, 255] are input into a lamp system of the RGB atmosphere lamp and can be converted into PWM waves to be input into LEDs with three different colors of red, green and blue, different R, G, B parameter combinations correspond to different mixed colors, mixed color values can be represented by 1937xy chromaticity coordinates x and y, and the R, G, B three primary color signal values greatly influence the luminous color of the RGB atmosphere lamp. Therefore, in step (1) of the method of the present invention, the neural network is constructed as: the input is R, G, B parameters and the output is chromaticity coordinates x, y. The influence of the self-characteristics of the lamp on the color mixing can also be identified through the neural network.
In this embodiment, the constructed neural network model may be a BP neural network model, and the topology structure thereof may be as shown in fig. 2.
As shown in fig. 2, in the present embodiment, the topology of the constructed BP neural network model may include: an input layer, a hidden layer, and an output layer. Wherein, the number of the input layer neurons is the number of the input features (R, G, B), namely three; the number of neuron nodes in the output layer is two, namely two, output characteristic numbers (x and y); the number of neuronal nodes of the hidden layer is referred to Kolmogorov theorem: the number s of hidden layer nodes is 2n +1(n is the number of input layer nodes), so in this embodiment, the number of hidden layer neurons can be set to 7.
It should be noted that, in the BP neural network model, each neuron includes information such as a weight, a threshold, and an activation function f (x). The mapping relationship between the output and the input of the neuron may be:
in the above formula (5), q is expressed as a neuron output, pjIs the input from the jth neuron, wjRepresents the connection weight of the input to the neuron, a represents the neuron threshold, and f (x) is the activation function.
Accordingly, in the present invention, a sigmoid function may be employed as the activation function f (x) of the BP neural network model instead of the step function.
FIG. 3 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting color according to the present invention on the training set x value by using the neural network model in one embodiment.
FIG. 4 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting color according to the invention on the y value of the training set by using a neural network model in one embodiment.
To further verify whether the trained neural network model of the present invention can recognize the actual RGB atmosphere lighting color, a preset R, G, B parameter may be input into the trained neural network model of the present invention, so as to obtain a comparison graph of the output of the neural network model and the output data of the training set, as shown in fig. 3 and fig. 4. As can be seen from fig. 3 and 4, in the present invention, the trained neural network model has a good identification effect, and the average error between the output data and the output data of the training set is less than 0.5%.
Correspondingly, five groups of data are selected outside the training set as the test set for further model verification, the input characteristics (R, G, B parameters) of the test set are input into the trained neural network model, and the error between the output value of the neural network model and the output value of the actual test set is compared and judged, as shown in fig. 5 and fig. 6.
FIG. 5 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting colors according to the invention on the test set x value by using a neural network model under one embodiment.
FIG. 6 schematically shows the predicted effect of the method for simulating RGB atmosphere lighting colors according to the invention on the y value of the test set by using a neural network model in one embodiment.
As shown in fig. 5 and 6, in the present invention, the input features (R, G, B parameters) of the test set are input into the trained neural network model, the trained neural network model has a good identification effect, and the average error between the output value of the trained neural network model and the output value of the actual test set is less than 0.8%.
In summary, the method for simulating RGB atmosphere lighting colors according to the present invention can use a neural network to simulate and identify the RGB atmosphere lighting colors offline, and the actual color values can be obtained by giving an input signal. The method can be separated from the actual environment, adjust and verify the atmosphere light color, and greatly simplify the judgment work and the calibration steps of the lamp, thereby effectively improving the development efficiency of the lamp and having very good popularization prospect and application value.
It should be noted that the prior art in the protection scope of the present invention is not limited to the examples given in the present application, and all the prior art which is not inconsistent with the technical scheme of the present invention, including but not limited to the prior patent documents, the prior publications and the like, can be included in the protection scope of the present invention.
In addition, the combination of the features in the present application is not limited to the combination described in the claims of the present application or the combination described in the embodiments, and all the features described in the present application may be freely combined or combined in any manner unless contradictory to each other.
It should also be noted that the above-mentioned embodiments are only specific embodiments of the present invention. It is apparent that the present invention is not limited to the above embodiments and similar changes or modifications can be easily made by those skilled in the art from the disclosure of the present invention and shall fall within the scope of the present invention.
Claims (9)
1. A method for simulating RGB atmosphere light colors, comprising:
(1) constructing a neural network model, the neural network being constructed to: the input is R, G, B parameters, and the output is chromaticity coordinates x and y;
(2) training sample data are collected based on an actual RGB atmosphere lamp;
(3) preprocessing the training sample data;
(4) training the neural network model by adopting the preprocessed training sample data until the training is finished;
(5) preset R, G, B parameters are input into the trained neural network model, which outputs simulated chromaticity coordinates.
2. The method for simulating RGB atmosphere lighting colors according to claim 1, wherein the neural network model is a BP neural network model.
3. The method of claim 2, wherein the BP neural network model comprises an input layer, a hidden layer and an output layer, wherein the number of hidden layer neurons is 7.
4. The method for simulating RGB ambience light colors as claimed in claim 2, wherein a sigmoid function is used as the activation function of the BP neural network model.
5. The method for simulating RGB atmosphere light colors according to claim 1, wherein in step (2), different R, G, B are given to the actual RGB atmosphere light, the corresponding chromaticity coordinates x, y are obtained by actual measurement, and all the actually given R, G, B and its corresponding chromaticity coordinates x, y are used as training sample data.
6. The method for simulating RGB atmosphere light colors of claim 1, wherein in the step (3), the preprocessing includes a normalization process.
7. The method for simulating RGB atmosphere light colors according to claim 1, wherein in the step (4), the neural network model is trained by using a damped least squares algorithm.
8. The method for simulating RGB atmosphere light colors according to claim 1, wherein in the step (4), the objective function e (w) of the training process is:
in the formula: y isiRepresenting a target chromaticity value; y isi' denotes the actual chromaticity value of the RGB atmosphere lamp; p represents the number of training samples; w represents weight and threshold vectors; e.g. of the typei(w) denotes a chromaticity coordinate learning error, and i denotes an ith training sample.
9. The method for simulating RGB atmosphere light colors of claim 8, wherein in the step (4), the training is completed when the objective function is < 0.0001.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110123140.8A CN112989689A (en) | 2021-01-29 | 2021-01-29 | Method for simulating RGB atmosphere light color |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110123140.8A CN112989689A (en) | 2021-01-29 | 2021-01-29 | Method for simulating RGB atmosphere light color |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112989689A true CN112989689A (en) | 2021-06-18 |
Family
ID=76345780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110123140.8A Pending CN112989689A (en) | 2021-01-29 | 2021-01-29 | Method for simulating RGB atmosphere light color |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989689A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114189970A (en) * | 2022-02-15 | 2022-03-15 | 广州地铁设计研究院股份有限公司 | Online learning-based intelligent lamp backup control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105611694A (en) * | 2015-12-30 | 2016-05-25 | 北京经纬恒润科技有限公司 | Color configuration method and apparatus for atmosphere lamp |
| CN107560829A (en) * | 2017-07-14 | 2018-01-09 | 伟创力电子技术(苏州)有限公司 | A kind of method of testing of three primary colours automatic decision LED color |
| CN109005617A (en) * | 2018-07-06 | 2018-12-14 | 上海北汇信息科技有限公司 | A kind of non-pole light regulating method and apparatus based on vehicle-mounted RGB controller |
| CN111458029A (en) * | 2020-03-03 | 2020-07-28 | 东莞职业技术学院 | Visible light MIMO communication system color detection method based on self-association neural network |
| US20200240601A1 (en) * | 2016-02-01 | 2020-07-30 | Hanxin ZHANG | Lighting device for creating atmosphere of living environment |
-
2021
- 2021-01-29 CN CN202110123140.8A patent/CN112989689A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105611694A (en) * | 2015-12-30 | 2016-05-25 | 北京经纬恒润科技有限公司 | Color configuration method and apparatus for atmosphere lamp |
| US20200240601A1 (en) * | 2016-02-01 | 2020-07-30 | Hanxin ZHANG | Lighting device for creating atmosphere of living environment |
| CN107560829A (en) * | 2017-07-14 | 2018-01-09 | 伟创力电子技术(苏州)有限公司 | A kind of method of testing of three primary colours automatic decision LED color |
| CN109005617A (en) * | 2018-07-06 | 2018-12-14 | 上海北汇信息科技有限公司 | A kind of non-pole light regulating method and apparatus based on vehicle-mounted RGB controller |
| CN111458029A (en) * | 2020-03-03 | 2020-07-28 | 东莞职业技术学院 | Visible light MIMO communication system color detection method based on self-association neural network |
Non-Patent Citations (2)
| Title |
|---|
| 廖宁放: "基于人工神经网络的CRT色度变换方法", 《中国优秀博硕士学位论文全文数据库（博士）-基础科学辑》 * |
| 彭波等: "《TCS230颜色传感器结合BP神经网络在颜色识别系统上的研究》", 《食品与机械》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114189970A (en) * | 2022-02-15 | 2022-03-15 | 广州地铁设计研究院股份有限公司 | Online learning-based intelligent lamp backup control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101757090B1 (en) | Systems and methods for texture assessment of a coating formulation | |
| US8392347B2 (en) | Coating color database creating method, search method using the database, their system, program, and recording medium | |
| KR102073046B1 (en) | How to check the texture parameters of the paint | |
| CN107465459B (en) | Indoor visible light positioning method based on color space intensity distribution | |
| CN111126134B (en) | Radar radiation source deep learning identification method based on non-fingerprint signal eliminator | |
| CN105102946B (en) | System and method for multithread color-match | |
| CN111818449B (en) | Visible light indoor positioning method based on improved artificial neural network | |
| US20160321546A1 (en) | Method and system for determining a color formula | |
| CN112989689A (en) | Method for simulating RGB atmosphere light color | |
| CN106053024B (en) | A kind of LED light source preference degree prediction technique towards monochromatic system object | |
| KR20050088116A (en) | Transformation structures for approximating color matching functions | |
| CN105424598A (en) | Motor vehicle exhaust detecting method based on image recognition | |
| CN114241272B (en) | Heterogeneous information fusion positioning method based on deep learning | |
| CN107271928A (en) | A kind of LED lamp temperature step drop aging testing method and device | |
| CN110889207A (en) | System combination model credibility intelligent evaluation method based on deep learning | |
| Labayrade et al. | Validation of Velux Daylight Visualizer 2 against CIE 171: 2006 test cases | |
| CN113033777B (en) | Vehicle-mounted atmosphere lamp chromaticity calibration method based on neural network calibration model | |
| CN106908150A (en) | Embedded system correlated colour temperature quick calculation method | |
| CN115236591B (en) | Indoor visible light positioning method based on machine learning mode | |
| CN208156464U (en) | Fluorescence temperature demodulating system based on radial base neural net | |
| CN115665917A (en) | LED eye-protecting lamp light intensity calculation method for simulating classroom illumination | |
| CN111860987B (en) | Method and device for predicting emission spectrum of mixed fluorescent material | |
| JPH11228877A (en) | Color matching capable of finding formulation of colorant and delustering agent in coating material by calculation | |
| CN107462330A (en) | A kind of color identification method and system | |
| CN110598289B (en) | Antenna temperature field measurement method under incomplete information |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |