Lamplight interaction control method and system for realizing interaction

By sampling the location and face orientation of the population, using neural networks to predict the light interaction type, and adjusting the light in combination with the distance factor, the problem of incomplete consideration of population characteristics in the existing technology is solved, and more targeted and rich lighting interaction display is achieved.

CN119095230AActive Publication Date: 2024-12-06LIFANG DIGITAL TECH GRP CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411271427.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-12-06
Estimated Expiration
2044-09-11

AI Technical Summary

Technical Problem

The existing lighting interaction control methods cannot fully consider the characteristics of the population, resulting in the inadequate targeted and rich lighting interaction display.

Method used

By sampling the position coordinates and face orientation of the interaction target, the position and light interaction type are predicted using a recurrent neural network or long and short-term memory network, combined with the face orientation and distance factors, the light interaction type probability parameters are obtained, and the light is periodically adjusted to cope with real-time changes.

Benefits of technology

It realizes a more targeted and rich interactive display of lights, flexibly adjusts the lights to deal with changes in the location and orientation of the crowd, and improves the comprehensiveness and targetedness of light control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119095230A_ABST
    Figure CN119095230A_ABST
Patent Text Reader

Abstract

The invention provides a lamplight interaction control method and system for realizing interaction, relates to the technical field of lamplight interaction design, and aims to realize more targeted and richer lamplight interaction display through more comprehensive crowd feature consideration. Comprising the following steps: respectively sampling position coordinates of each interactive target in a first time period at equal time intervals; predicting a predicted position coordinate of each interactive target at an intermediate time point of the second time period based on the first model; respectively sampling the face orientation of each interactive target at each position coordinate and a distance factor relative to each lamplight point location; respectively acquiring light interaction type probability parameters according to the face orientation array and the distance factor based on a second model; respectively acquiring all adaptive interaction targets of each lamplight point location at an intermediate time point of the second time period; and obtaining the interactive light type of the light point location in the second time period. The method has the advantage that lamplight interaction control is more flexible and comprehensive.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of lighting interaction design, and in particular to a lighting interaction control method and system for realizing interaction. Background Art

[0002] Interactive lighting displays have gradually become a common decorative setting in various exhibition halls and other display or entertainment venues.

[0003] In order to achieve a better interactive display of lights, it is necessary to control the light interaction more specifically according to the characteristics of the crowd. In the prior art, the light interaction can be controlled according to the characteristics of the crowd, or the light can be adjusted simply according to the orientation of each person, but these forms of control are relatively simple and are not conducive to a more comprehensive and targeted interactive display of lights.

[0004] Therefore, it is necessary to optimize the lighting interaction control method and achieve more targeted and richer lighting interaction displays by considering more comprehensive crowd characteristics. Summary of the invention

[0005] The object of the present invention is to provide an interactive lighting control method and system, which can achieve more targeted and richer lighting interactive display by considering more comprehensive crowd characteristics.

[0006] The embodiments of the present invention are implemented by the following technical solutions:

[0007] The present invention first provides a lighting interactive control method, comprising the following steps:

[0008] The position coordinates of each interactive target in the first time period are sampled at equal time intervals to obtain a position coordinate array;

[0009] Predicting the predicted position coordinates of each interactive target at a middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is a time period next to the first time period;

[0010] Sample the facial orientation of each interactive target at each position coordinate and the distance factor relative to each light point respectively to obtain a facial orientation array and a distance factor array;

[0011] Based on the second model, the light interaction type probability parameters clas are obtained according to the face orientation array and the distance factor. ij ,clas ij represents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period;

[0012] Respectively obtain all adaptive interaction targets of each light point at the middle time point of the second time period;

[0013] According to the light interaction type probability parameter clas of all the adapted interactive targets of the light point, ij Obtain the interactive light type of the light point in the second time period.

[0014] Preferably, the first model adopts a recurrent neural network or a long short-term memory network.

[0015] Preferably, the second model comprises an input layer, a first feature extraction layer, a second feature extraction layer, a concatenation layer and a classification output layer;

[0016] The input layer is used to receive the face orientation array and the distance factor array;

[0017] The first feature extraction layer is used to extract a first feature matrix according to the facial orientation array;

[0018] The second feature extraction layer is used to extract a second feature matrix according to the first feature matrix and the distance factor array;

[0019] The splicing layer is used to splice the first feature matrix and the second feature matrix to obtain a fused feature matrix;

[0020] The classification output layer is used to output the light interaction type probability parameter clas according to the fusion feature matrix ij .

[0021] Preferably, the expression of the first feature extraction layer is:

[0022]

[0023] Among them, SP i 1 is the first feature matrix of the i-th interactive target, N is the total number of light points, For SP i 1 The jth element in the first time period, m represents the mth sampling of the data in the first time period, M is the total number of sampling data in the first time period, e is a natural constant, ln(.) is a natural logarithm function, min j (.,.) is a function that takes the minimum value based on the change of j, δ is the preset angle difference threshold, ag ij,m Represents the angle between the vector pointing from the ith interactive target to the jth light point and the facial orientation of the ith interactive target at the mth sampling time. round(.) represents the rounding function. char ij,mRepresents the intermediate parameter of the i-th interactive target relative to the j-th lighting point at the m-th sampling. if is a truth judgment function and returns 1 if the judgment object is true, otherwise returns 0.

[0024] Preferably, the expression of the second feature extraction layer is:

[0025]

[0026] Among them, SP i 2 is the second feature matrix of the i-th interactive target, N is the total number of light points, For SP i 2 The jth element in d ij,m is the distance factor from the ith interactive target to the jth light point at the mth sampling, L iq,m and L ij,m are the distances from the ith interactive target to the qth and jth light points at the mth sampling time, respectively, th is the preset distance threshold.

[0027] Preferably, the expression of the splicing layer is:

[0028]

[0029] Among them, SP i mix is the fusion feature matrix.

[0030] Preferably, the expression of the classification output layer is:

[0031]

[0032] α+β=1;

[0033] Among them, α and β are weights to be trained.

[0034] Preferably, the method for respectively acquiring all the adaptive interactive targets of each light point at the middle time point of the second time period is:

[0035] Obtaining the distance from the interactive target to each of the light points based on the predicted position coordinates of the interactive target at the middle time point of the second time period;

[0036] The light point that is closest to the interactive target is obtained, and the interactive target is the adapted interactive target corresponding to the light point.

[0037] Preferably, the light interaction type probability parameters clas of all the adapted interactive targets of the light point are respectively ij The method to obtain the interactive light type of the light point in the second time period is:

[0038] Get the light interaction type probability parameter clas of each of the adapted interactive targets respectively ij ;

[0039] Calculate the evaluation parameters of each of the adaptation interaction targets separately:

[0040]

[0041] Among them, evp k is the evaluation parameter of the kth adaptation interaction target at the lighting point, i k represents the number of the kth adapted interaction target among all the interaction targets, that is, For the i k The probability that the recommended light interaction type of the jth interactive target in the second time period is the light interaction type of the jth light point in the first time period, e is a natural constant, N is the total number of light points, and am k The value of the light interaction type probability parameter of the kth adapted interactive target is greater than the probability parameter threshold The number of max3 is the sum of the three largest values ​​of the light interaction type probability parameters of the kth adapted interaction target;

[0042] Obtaining a modified weight based on the evaluation parameters:

[0043]

[0044] Among them, corre k is the correction coefficient of the kth adaptive interactive target at the light point, V is the total number of adaptive interactive targets at the light point, evp v is the evaluation parameter of the vth adaptation interaction target of the light point;

[0045] Get the probability comprehensive parameters of each interactive light type respectively:

[0046]

[0047] Among them, J j a probability correction parameter representing that the recommended light interaction type in the second time period is the light interaction type of the j-th light point in the first time period, and k is the total number of the adapted interaction targets;

[0048] Get the value of J with the maximum probability correction parameter jmax , jmax∈[1,N], the interactive lighting type of the lighting point in the second time period is the lighting interaction type of the jmax-th lighting point in the first time period.

[0049] In order to solve the above problems, the present invention further provides an interactive lighting control system, which is applied to any one of the above-mentioned interactive lighting control methods, and is characterized by comprising:

[0050] A first sampling module is used to sample the position coordinates of each interactive target in a first time period at equal time intervals to obtain a position coordinate array;

[0051] A prediction module, configured to predict the predicted position coordinates of each interactive target at a middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is a time period next to the first time period;

[0052] The second sampling module is used to sample the facial orientation of each interactive target at each position coordinate and the distance factor relative to each light point to obtain a facial orientation array and a distance factor array;

[0053] The type recognition module is used to obtain the light interaction type probability parameter clas according to the face orientation array and the distance factor based on the second model. ij ,clas ij represents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period;

[0054] An adaptive interactive target acquisition module, used to respectively acquire all adaptive interactive targets of each light point at the middle time point of the second time period;

[0055] The interactive lighting type judgment module is used to determine the lighting interaction type probability parameters clas of all the adaptive interactive targets of the lighting point. ij Obtain the interactive light type of the light point in the second time period.

[0056] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0057] The present invention can adjust the lighting periodically, and the adjustment is flexible, which is convenient for coping with real-time changes. Each adjustment is based on the crowd position and face orientation data of the next cycle calculated based on the data of the previous cycle to determine the lighting adjustment plan, so that the lighting adjustment is more targeted to the characteristics of the crowd.

[0058] When extracting features through face orientation data, the present invention takes into account the influence of the observation tendency of the person and the distance factor on the observation tendency, thereby achieving more comprehensive feature considerations and improving the pertinence and richness when adjusting the lighting type;

[0059] After obtaining the comprehensive characteristics of each person, the present invention classifies and processes them according to the distance from the lighting point, and assigns different weights to different people based on the characteristics of the observation population at the lighting point to obtain the final lighting adjustment type, further improving the comprehensiveness of the control considerations;

[0060] The present invention has reasonable design, is easy to be applied to various lighting display interactive scenes, and is easy to promote and implement. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A schematic diagram of a lighting interactive control method for implementing interaction provided in Embodiment 1 of the present invention;

[0062] Figure 2 A schematic diagram of the structure of the second model provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0064] Example 1

[0065] This embodiment provides a method for realizing interactive lighting control. Figure 1 , including the following steps:

[0066] Step S1: sampling the position coordinates of each interactive target in a first time period at equal time intervals to obtain a position coordinate array;

[0067] Step S2: predicting the predicted position coordinates of each interactive target at the middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is the next time period of the first time period;

[0068] Step S3: respectively sampling the facial orientation of each interactive target at each position coordinate and the distance factor relative to each light point to obtain a facial orientation array and a distance factor array;

[0069] Step S4: Based on the second model, obtain the light interaction type probability parameter clas according to the face orientation array and the distance factor. ij ,clas ij represents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period;

[0070] Step S5: respectively obtaining all adaptive interaction targets of each light point at the middle time point of the second time period;

[0071] Step S6: respectively calculate the light interaction type probability parameters clas of all the adaptive interaction targets of the light point ij Obtain the interactive light type of the light point in the second time period.

[0072] As a preferred solution of this embodiment, the first model in step S2 adopts a recurrent neural network or a long short-term memory network. Both networks are relatively mature state prediction networks and can be used in this embodiment to predict the position state of the interactive target. It is particularly noted that the facial orientation of step S3 can be estimated by existing deep learning models, such as OpenPose and MediaPipe. The sampling of facial orientation and position information can be achieved by arranging a camera device in the scene.

[0073] This embodiment performs position prediction based on the sampling data of a time period, with the purpose of predicting the appropriate audience interaction target for each lighting point in the next time period, and extracting the facial orientation array and the distance factor array to consider the most suitable lighting interaction type for each audience interaction target in the next time period. Based on the above data acquisition, the lighting interaction type arrangement of each lighting point in the next time period is formulated, so as to achieve comprehensive and flexible lighting control.

[0074] Example 2

[0075] This embodiment is based on the technical solution of Embodiment 1 and further explains the specific implementation method of each step.

[0076] In this embodiment, see Figure 2 , the second model in step S4 includes an input layer, a first feature extraction layer, a second feature extraction layer, a concatenation layer and a classification output layer;

[0077] The input layer is used to receive the face orientation array and the distance factor array;

[0078] The first feature extraction layer is used to extract a first feature matrix according to the facial orientation array;

[0079] The second feature extraction layer is used to extract a second feature matrix according to the first feature matrix and the distance factor array;

[0080] The splicing layer is used to splice the first feature matrix and the second feature matrix to obtain a fused feature matrix;

[0081] The classification output layer is used to output the light interaction type probability parameter clas according to the fusion feature matrix ij .

[0082] First, the expression of the first feature extraction layer is preferably:

[0083]

[0084] Among them, SP i 1 is the first feature matrix of the i-th interactive target, N is the total number of light points, For SP i 1 The jth element in the first time period, m represents the mth sampling of the data in the first time period, M is the total number of sampling data in the first time period, e is a natural constant, ln(.) is a natural logarithm function, min j (.,.) is a function that takes the minimum value based on the change of j, δ is a preset angle difference threshold, for example, it can be 30 degrees, ag ij,m Represents the angle between the vector pointing from the ith interactive target to the jth light point and the facial orientation of the ith interactive target at the mth sampling time. round(.) represents the rounding function. char ij,m Represents the intermediate parameter of the i-th interactive target relative to the j-th lighting point at the m-th sampling. if is a truth judgment function and returns 1 if the judgment object is true, otherwise returns 0.

[0085] The first feature extraction layer here is used to extract facial orientation information, taking into account the positions of lights within a certain angle range of the facial orientation.

[0086] Furthermore, the expression of the second feature extraction layer is preferably:

[0087]

[0088] Among them, SP i 2 is the second feature matrix of the i-th interactive target, N is the total number of light points, For SP i 2 The jth element in d ij,mis the distance factor from the ith interactive target to the jth light point at the mth sampling, L iq,m and L ij,m are the distances from the ith interactive target to the qth and jth light points at the mth sampling time, respectively, th is the preset distance threshold. iq,m and L ij,m That is extracted from the distance factor array.

[0089] Preferably, the expression of the splicing layer is:

[0090]

[0091] Among them, SP i mix is the fusion feature matrix.

[0092] As a further preferred solution, the expression of the classification output layer is:

[0093]

[0094] α+β=1;

[0095] Among them, α and β are weights to be trained.

[0096] The purpose of adding the second feature extraction layer in this embodiment is to extract the distance information from the interactive target to each lighting point. Because the viewing tendency extracted from the facial orientation of the interactive panel will be affected by the distance rather than simply the preference, and the viewing tendency extracted from the facial orientation will also be reduced when the preference is not high at close distance, it is possible that the viewing frequency is higher due to the close distance. Therefore, this embodiment integrates the two feature data, comprehensively considers the viewing tendency and distance factors, and tries to match the types that cannot be seen because the distance is too far, or the types with particularly strong viewing intentions. Therefore, this embodiment is able to achieve more comprehensive feature considerations, and thus obtain a more detailed and highly matched lighting control solution.

[0097] In this embodiment, the method of obtaining all the adaptive interactive targets of each light point at the middle time point of the second time period in step S5 is preferably:

[0098] Obtaining the distance from the interactive target to each of the light points based on the predicted position coordinates of the interactive target at the middle time point of the second time period;

[0099] The light point that is closest to the interactive target is obtained, and the interactive target is the adapted interactive target corresponding to the light point.

[0100] Finally, in step S6, the light interaction type probability parameters clas of all the adaptive interactive targets of the light point are respectively ij The method to obtain the interactive light type of the light point in the second time period is:

[0101] Get the light interaction type probability parameter clas of each of the adapted interactive targets respectively ij ;

[0102] Calculate the evaluation parameters of each of the adaptation interaction targets separately:

[0103]

[0104] Among them, evp k is the evaluation parameter of the kth adaptation interaction target at the lighting point, i k represents the number of the kth adapted interaction target among all the interaction targets, that is, For the i k The probability that the recommended light interaction type of the jth interactive target in the second time period is the light interaction type of the jth light point in the first time period, e is a natural constant, N is the total number of light points, and am k The value of the light interaction type probability parameter of the kth adapted interactive target is greater than the probability parameter threshold The number of max3 is the sum of the three largest values ​​of the light interaction type probability parameters of the kth adapted interaction target;

[0105] Obtaining a modified weight based on the evaluation parameters:

[0106]

[0107] Among them, corre k is the correction coefficient of the kth adaptive interactive target at the light point, V is the total number of adaptive interactive targets at the light point, evp v is the evaluation parameter of the vth adaptation interaction target of the light point;

[0108] Get the probability comprehensive parameters of each interactive light type respectively:

[0109]

[0110] Among them, J j a probability correction parameter representing that the recommended light interaction type in the second time period is the light interaction type of the j-th light point in the first time period, and k is the total number of the adapted interaction targets;

[0111] Get the value of J with the maximum probability correction parameter jmax , jmax∈[1,N], the interactive lighting type of the lighting point in the second time period is the lighting interaction type of the jmax-th lighting point in the first time period.

[0112] This embodiment finally modifies the probability parameters of each light interaction type of each adaptive interactive target of each light point, that is, assigns different calculation weights to each adaptive interactive target to compare which light interaction type probability parameter of this light point has the highest comprehensive evaluation. Assigning different calculation weights to each adaptive interactive target is mainly determined by the distribution of the predicted probability of each adaptive interactive target, that is, assigning higher weights to adaptive interactive targets with greater tendencies. As a further optimization, this embodiment can also consider comprehensive coverage of types when assigning light interaction types to each light point in the second time period, that is, the number of light points is set to be greater than or equal to the light interaction type, and when assigning, it is ensured that each light interaction type appears as much as possible. For example, if there are unassigned light interaction types after the assignment is completed, then find the light interaction type with the most assignments, and find the one with the lowest comprehensive probability parameter to replace it with the unassigned light interaction type.

[0113] Example 3

[0114] This embodiment provides an interactive lighting control system for realizing interaction, which is applied to any one of the above-mentioned interactive lighting control methods for realizing interaction, and is characterized by comprising:

[0115] A first sampling module is used to sample the position coordinates of each interactive target in a first time period at equal time intervals to obtain a position coordinate array;

[0116] A prediction module, configured to predict the predicted position coordinates of each interactive target at a middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is a time period next to the first time period;

[0117] The second sampling module is used to sample the facial orientation of each interactive target at each position coordinate and the distance factor relative to each light point to obtain a facial orientation array and a distance factor array;

[0118] The type recognition module is used to obtain the light interaction type probability parameter clas according to the face orientation array and the distance factor based on the second model. ij ,clas ijrepresents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period;

[0119] An adaptive interactive target acquisition module, used to respectively acquire all adaptive interactive targets of each light point at the middle time point of the second time period;

[0120] The interactive lighting type judgment module is used to determine the lighting interaction type probability parameters clas of all the adaptive interactive targets of the lighting point. ij Obtain the interactive light type of the light point in the second time period.

[0121] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for realizing interactive lighting control, characterized in that: The following steps are involved: The position coordinates of each interactive target in the first time period are sampled at equal time intervals to obtain a position coordinate array; Predicting the predicted position coordinates of each interactive target at a middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is a time period next to the first time period; Sample the facial orientation of each interactive target at each position coordinate and the distance relative to each light point to obtain a facial orientation array and a distance factor array; Based on the second model, the light interaction type probability parameters clas are obtained according to the face orientation array and the distance factor. ij ,clas ij represents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period; Respectively obtain all adaptive interaction targets of each light point at the middle time point of the second time period; According to the light interaction type probability parameter clas of all the adapted interactive targets of the light point, ij Obtain the interactive light type of the light point in the second time period.

2. The interactive lighting control method according to claim 1, characterized in that: The first model adopts a recurrent neural network or a long short-term memory network.

3. The interactive lighting control method according to claim 1, characterized in that: The second model includes an input layer, a first feature extraction layer, a second feature extraction layer, a concatenation layer, and a classification output layer; The input layer is used to receive the face orientation array and the distance factor array; The first feature extraction layer is used to extract a first feature matrix according to the facial orientation array; The second feature extraction layer is used to extract a second feature matrix according to the first feature matrix and the distance factor array; The splicing layer is used to splice the first feature matrix and the second feature matrix to obtain a fused feature matrix; The classification output layer is used to output the light interaction type probability parameter clas according to the fusion feature matrix ij .

4. The interactive lighting control method according to claim 3, characterized in that: The expression of the first feature extraction layer is: j=1,2,…,N; Among them, SP i 1 is the first feature matrix of the i-th interactive target, N is the total number of light points, For SP i 1 The jth element in the first time period, m represents the mth sampling of the data in the first time period, M is the total number of sampling data in the first time period, e is a natural constant, ln(.) is a natural logarithm function, min j (.,.) is a function that takes the minimum value based on the change of j, δ is the preset angle difference threshold, ag ij,m Represents the angle between the vector pointing from the ith interactive target to the jth light point and the facial orientation of the ith interactive target at the mth sampling time. round(.) represents the rounding function. char ij,m Represents the intermediate parameter of the i-th interactive target relative to the j-th lighting point at the m-th sampling. if is a truth judgment function and returns 1 if the judgment object is true, otherwise returns 0.

5. The interactive lighting control method according to claim 4, characterized in that: The expression of the second feature extraction layer is: Among them, SP i 2 is the second feature matrix of the i-th interactive target, N is the total number of light points, For SP i 2 The jth element in d ij,m is the distance factor from the ith interactive target to the jth light point at the mth sampling, L iq,m and L ij,m are the distances from the ith interactive target to the qth and jth light points at the mth sampling time, respectively, th is the preset distance threshold.

6. The interactive lighting control method according to claim 5, characterized in that: The expression of the splicing layer is: Among them, SP i mix is the fusion feature matrix.

7. The interactive lighting control method according to claim 6, characterized in that: The expression of the classification output layer is: α+β=1; Among them, α and β are weights to be trained.

8. The interactive lighting control method according to claim 1, characterized in that: The method of respectively obtaining all the adaptive interaction targets of each light point at the middle time point of the second time period is: Obtaining the distance from the interactive target to each of the light points based on the predicted position coordinates of the interactive target at the middle time point of the second time period; The light point that is closest to the interactive target is obtained, and the interactive target is the adapted interactive target corresponding to the light point.

9. The interactive lighting control method according to claim 8, characterized in that: According to the light interaction type probability parameter clas of all the adapted interactive targets of the light point, ij The method to obtain the interactive light type of the light point in the second time period is: Get the light interaction type probability parameter clas of each of the adapted interactive targets respectively ij ; Calculate the evaluation parameters of each of the adaptation interaction targets separately: Among them, evp k is the evaluation parameter of the kth adaptation interaction target at the lighting point, i k represents the number of the kth adapted interaction target among all the interaction targets, that is, For the i k The probability that the recommended light interaction type of the jth interactive target in the second time period is the light interaction type of the jth light point in the first time period, e is a natural constant, N is the total number of light points, and am k The value of the light interaction type probability parameter of the kth adapted interactive target is greater than the probability parameter threshold The number of max3 is the sum of the three largest values ​​of the light interaction type probability parameters of the kth adapted interaction target; Obtaining a modified weight based on the evaluation parameters: Among them, corre k is the correction coefficient of the kth adaptive interactive target at the light point, V is the total number of adaptive interactive targets at the light point, evp v is the evaluation parameter of the vth adaptation interaction target of the light point; Get the probability comprehensive parameters of each interactive light type respectively: Among them, J j a probability correction parameter representing that the recommended light interaction type in the second time period is the light interaction type of the j-th light point in the first time period, and k is the total number of the adapted interaction targets; Get the value of J with the maximum probability correction parameter jmax , jmax∈[1,N], the interactive lighting type of the lighting point in the second time period is the lighting interaction type of the jmax-th lighting point in the first time period.

10. An interactive lighting control system for realizing interaction, applied to an interactive lighting control method for realizing interaction as claimed in any one of claims 1 to 9, characterized in that: include: A first sampling module is used to sample the position coordinates of each interactive target in a first time period at equal time intervals to obtain a position coordinate array; A prediction module, configured to predict the predicted position coordinates of each interactive target at a middle time point of a second time period based on the first model and the position coordinate array, wherein the second time period is a time period next to the first time period; The second sampling module is used to sample the facial orientation of each interactive target at each position coordinate and the distance factor relative to each light point to obtain a facial orientation array and a distance factor array; The type recognition module is used to obtain the light interaction type probability parameter clas according to the face orientation array and the distance factor based on the second model. ij ,clas ij represents the probability that the recommended light interaction type of the i-th interactive target in the second time period is the light interaction type of the j-th light point in the first time period; An adaptive interactive target acquisition module, used to respectively acquire all adaptive interactive targets of each light point at the middle time point of the second time period; The interactive lighting type judgment module is used to determine the lighting interaction type probability parameters clas of all the adaptive interactive targets of the lighting point. ij Obtain the interactive light type of the light point in the second time period.

Citation Information

Patent Citations

  • Light interaction control information transmission method and system

    CN116455522A

  • Intelligent lighting control method and system of simulation three-dimensional map based on scene fusion

    CN116847508A

  • Simulation model light interaction control method and system for theme park audience interaction

    CN116939923A

  • LED energy-saving control method and system based on Internet of Things, and medium

    CN118301821A

  • A centralized model predictive lighting control method and a centralized prediction-based controllable street lighting system

    EP4369866A1