Light source adjusting method and system

Abstract

The invention discloses a light source adjustment method and system, and relates to the technical field of light source adjustment. The light source adjustment method comprises the steps of obtaining light source adjustment data of a to-be-adjusted landscape vehicle lamp in real time, performing data adjustment analysis to obtain a vehicle condition adjustment index and an emotional response adjustment index of the to-be-adjusted landscape vehicle lamp, obtaining historical light source data set for a plurality of historical times of the to-be-adjusted landscape vehicle lamp, and performing analysis to obtain a preference adjustment index; according to the invention, intelligent light source adjustment is carried out based on the light source adjustment index of the to-be-adjusted landscape vehicle lamp, so that dynamic adjustment can be carried out according to the individual needs of a driver, and the adjustment accuracy of the to-be-adjusted landscape vehicle lamp is improved. And the landscape vehicle lamp is automatically adjusted according to different emotions, so that the arrangement of the landscape vehicle lamp is optimized, the most appropriate light source can be provided, and the driving safety and psychological comfort are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of light source adjustment, and specifically to a method and system for light source adjustment. Background Art

[0002] With the rapid development of the automotive industry, the functions of automobiles are not limited to providing convenient means of transportation. More and more consumers begin to pay attention to the comfort of the car interior and driving experience. Driven by this demand, landscape car lights, that is, interior atmosphere lights as a new type of car interior element, have gradually come into the view of car owners. Landscape car lights can not only enhance the visual effect inside the car, but also provide a more comfortable and personalized driving environment for car owners through different brightness, color temperature and color tone. The adjustment of interior atmosphere lights can significantly affect the driver's mood and mental state, thereby improving the driving experience. Especially during long nighttime driving, reasonable adjustment of landscape car lights can effectively relieve the driver's visual fatigue and enhance safety.

[0003] A prior art, such as a light source adjustment method and system disclosed in a patent application with publication number CN104105249A, the system includes: an opening module for opening a light source irradiation detection workbench; a photographing module for controlling an imaging device to photograph the reference block in real time; an acquisition module for acquiring images of the reference block at various positions around the detection workbench in real time; a calculation module for calculating the average brightness of each image; a judgment module for judging whether the average brightness of the acquired images is consistent; an adjustment module for adjusting the light source to make the average brightness of the images consistent; a statistics module for counting the number of pixels distributed in multiple preset brightness sections in each image; an adjustment module for, when the number of pixels in multiple brightness sections is inconsistent, adjusting the light source to make the number of pixels in the multiple brightness sections consistent. The present invention adjusts the light source to make the number of pixels in multiple preset brightness sections of a reference object consistent, so as to realize that the light source is adjusted to be completely parallel to the test platform, which provides convenience for subsequent tests.

[0004] Based on the above solution, it is found that the limitations of the prior art at least include the following problems: the prior art lacks a real-time response mechanism for the personalized needs and emotional changes of drivers, and fails to fully integrate vehicle condition data and the driver's real-time feedback for dynamic adjustment of the light source, resulting in a relatively single and mechanical light source adjustment, which is difficult to flexibly meet the needs under nighttime driving conditions, and thus it is easy to cause the light source adjustment to be difficult to accurately match the actual needs of the driver in a specific scenario. Especially during nighttime driving, it is easy to have a situation where the light source does not suit the driver's needs or environmental changes, thereby affecting the driver's driving experience and driving safety. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a light source adjustment method and system, which solves the problem that the prior art fails to adjust the light source in real time according to the personalized needs and emotional changes of the driver, resulting in overly single light source adjustment, making it difficult to flexibly adapt to night driving conditions, and thus affecting the driving experience and safety.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A light source adjustment method includes the following steps: obtaining in real time the light source adjustment data of the landscape car lights to be adjusted, where the light source adjustment data includes vehicle condition data and driving facial image data; respectively performing data adjustment analysis on the light source adjustment data of the landscape car lights to be adjusted to obtain the vehicle condition adjustment index and emotion response adjustment index of the landscape car lights to be adjusted; simultaneously obtaining the historical light source data of several previous settings of the landscape car lights to be adjusted, and analyzing to obtain the preference adjustment index of the landscape car lights to be adjusted, and combining the vehicle condition adjustment index and emotion response adjustment index of the landscape car lights to be adjusted for comprehensive control analysis to obtain the light source control index of the landscape car lights to be adjusted; and performing intelligent light source adjustment based on the light source control index of the landscape car lights to be adjusted.

[0007] Further, the vehicle condition data includes the in-vehicle environment adjustment index, interior reflection index, and interior light absorption index, and the specific steps to obtain the vehicle condition adjustment index of the landscape car lights to be adjusted are as follows: comprehensively analyzing the in-vehicle environment adjustment index, interior reflection index, and interior light absorption index of the landscape car lights to be adjusted to obtain the in-vehicle light environment adjustment index of the landscape car lights to be adjusted; obtaining the driving speed adjustment index, steering adjustment index, and external light intensity value of the landscape car lights to be adjusted, and performing normalization processing with the in-vehicle light environment adjustment index; based on the normalized driving speed adjustment index, steering adjustment index, external light intensity value, and in-vehicle light environment adjustment index of the landscape car lights to be adjusted, performing comprehensive analysis to obtain the vehicle condition adjustment index of the landscape car lights to be adjusted.

[0008] Further, the specific formula for calculating the vehicle condition adjustment index of the landscape car lights to be adjusted is as follows: ; where is the vehicle condition adjustment index of the landscape car lights to be adjusted, is the normalized driving speed adjustment index of the landscape car lights to be adjusted, is the speed adjustment coefficient stored in the database, is the normalized external light intensity value of the landscape car lights to be adjusted, is the external light adjustment coefficient stored in the database, is the normalized steering adjustment index of the landscape car lights to be adjusted, is the steering adjustment coefficient stored in the database, is the normalized in-vehicle light environment adjustment index of the landscape car lights to be adjusted, is the internal and external difference adjustment coefficient stored in the database.

[0009] Furthermore, the driving facial image data is specifically the pixel value and two-dimensional coordinates of each pixel point in the driving facial image, and the specific steps to obtain the emotion response adjustment index of the landscape lamp to be adjusted are as follows: Input the pixel value and two-dimensional coordinates of each pixel point in the driving facial image of the landscape lamp to be adjusted into a pre-trained facial expression recognition model for predictive analysis to obtain the emotion feedback set of the landscape lamp to be adjusted, that is, the emotion perception index, the emotion reaction sensitivity index, and the emotion adaptation index; and comprehensively analyze the emotion perception index, the emotion reaction sensitivity index, and the emotion adaptation index of the landscape lamp to be adjusted to obtain the emotion response adjustment index of the landscape lamp to be adjusted.

[0010] Furthermore, the specific formula for calculating the emotion response adjustment index of the landscape lamp to be adjusted is as follows: ; where is the emotion response adjustment index of the landscape lamp to be adjusted, is the emotion perception index of the landscape lamp to be adjusted, is the perception coefficient stored in the database, is the perception adjustment coefficient stored in the database, is the emotion reaction sensitivity index of the landscape lamp to be adjusted, is the reaction sensitivity index stored in the database, is the reaction sensitivity adjustment index stored in the database, is the emotion adaptation index of the landscape lamp to be adjusted, is the adaptation coefficient stored in the database, is the adaptation adjustment index stored in the database, is the superposition adjustment index stored in the database, .

[0011] Further, the facial expression recognition model is specifically a deep convolutional neural network, which includes an input layer, several convolutional layers, a non-linear activation layer, a pooling layer, a flattening layer, a fully-connected layer, and a regression output layer. The specific steps to obtain the emotion feedback set of the landscape vehicle lamp to be adjusted are as follows: In the input layer of the deep convolutional neural network, receive the driving facial image data of the landscape vehicle lamp to be adjusted and perform preprocessing; in the convolutional layer of the deep convolutional neural network, perform feature extraction processing on the preprocessed driving facial image data of the landscape vehicle lamp to be adjusted to obtain the facial feature map of the landscape vehicle lamp to be adjusted; in the non-linear activation layer of the deep convolutional neural network, perform non-linear activation processing on the facial feature map of the landscape vehicle lamp to be adjusted; in the pooling layer of the deep convolutional neural network, perform dimensionality reduction processing on the non-linearly activated facial feature map of the landscape vehicle lamp to be adjusted to obtain the facial dimensionality-reduced feature map of the landscape vehicle lamp to be adjusted; in the flattening layer of the deep convolutional neural network, flatten the facial dimensionality-reduced feature map of the landscape vehicle lamp to be adjusted to obtain the facial feature vector of the landscape vehicle lamp to be adjusted; in the fully-connected layer of the deep convolutional neural network, perform feature fusion processing on the facial feature vector of the landscape vehicle lamp to be adjusted to obtain the facial complex feature vector of the landscape vehicle lamp to be adjusted; in the regression output layer of the deep convolutional neural network, perform regression prediction analysis on the facial feature vector of the landscape vehicle lamp to be adjusted to obtain the emotion perception index, emotion response sensitivity index, and emotion adaptation index of the landscape vehicle lamp to be adjusted, that is, the emotion feedback set.

[0012] Further, the historical light source data includes historical brightness values, historical color temperature values, historical hue values, historical light source saturation values, and historical gradient speed values. The specific steps to obtain the preference adjustment index of the landscape vehicle lamp to be adjusted are as follows: Comprehensively analyze the historical brightness values, historical color temperature values, historical hue values, historical light source saturation values, and historical gradient speed values set each time for the landscape vehicle lamp to be adjusted to obtain the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle lamp to be adjusted, and perform standardization processing; and comprehensively analyze the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle lamp to be adjusted after standardization processing to obtain the preference adjustment index of the landscape vehicle lamp to be adjusted.

[0013] Further, the specific formula for calculating the light source regulation index of the landscape vehicle lamp to be adjusted is as follows: ; where is the light source regulation index of the landscape vehicle lamp to be adjusted, is the vehicle condition adjustment index of the landscape vehicle lamp to be adjusted, is the vehicle condition adjustment coefficient in the database, is the emotion response adjustment index of the landscape car light to be adjusted, is the emotion regulation coefficient in the database, is the preference adjustment index of the landscape car light to be adjusted, is the preference regulation coefficient in the database, is the gain regulation coefficient in the database, is the composite regulation coefficient in the database.

[0014] Further, the specific steps for intelligent light source adjustment based on the light source regulation index of the landscape car light to be adjusted are as follows: Judge and analyze the light source regulation index of the landscape car light to be adjusted with the preset light source regulation index threshold; If the light source regulation index of the landscape car light to be adjusted is lower than the preset light source regulation index threshold, generate a corresponding gain control signal and adjust the landscape car light to be adjusted; If the light source regulation index of the landscape car light to be adjusted is not lower than the preset light source regulation index threshold, generate a corresponding reduction control signal and adjust the landscape car light to be adjusted.

[0015] A light source adjustment system includes an adjustment data acquisition module for real-time acquisition of the light source adjustment data of the landscape car light to be adjusted, where the light source adjustment data includes vehicle condition data and driving facial image data; An adjustment data analysis module for respectively performing data adjustment analysis on the light source adjustment data of the landscape car light to be adjusted to obtain the vehicle condition adjustment index and emotion response adjustment index of the landscape car light to be adjusted; A comprehensive adjustment analysis module for simultaneously acquiring the historical light source data of several previous settings of the landscape car light to be adjusted, analyzing to obtain the preference adjustment index of the landscape car light to be adjusted, and performing comprehensive regulation analysis in combination with the vehicle condition adjustment index and emotion response adjustment index of the landscape car light to be adjusted to obtain the light source regulation index of the landscape car light to be adjusted; An intelligent light source adjustment module for performing intelligent light source adjustment based on the light source regulation index of the landscape car light to be adjusted.

[0016] The present invention has the following beneficial effects: (1) This light source adjustment method can dynamically adjust according to the personalized needs of the driver by real-time acquisition of vehicle condition data and the driver's facial image data, combined with the emotion response adjustment index, and automatically adjust the landscape car light according to different emotions, thereby improving the driver's comfort, helping the driver stay alert, improving the driving experience, and combining the preference adjustment index to further optimize the landscape car light settings, and then ensuring that the most suitable light source can be provided, so as to achieve the effect of improving driving safety and psychological comfort.

[0017] (2) The light source adjustment method can provide a more adaptable headlight adjustment method during night driving by obtaining vehicle condition data in real time and combining it with the driver's emotional feedback. Especially when the driver's emotions fluctuate greatly, it can timely adjust the light source of the sightseeing vehicle, thereby helping the driver maintain a higher attention level and comfort, effectively reducing driving fatigue, and then improving the safety of night driving. When the driver is in a poor emotional state, the adjustment of the light source can provide a stress-relieving atmosphere, helping the driver maintain a good driving state and effectively reducing the probability of traffic accidents.

[0018] (3) The light source adjustment method combines the vehicle condition adjustment index, the emotional response adjustment index, and the historical light source data, and conducts comprehensive regulation and analysis to obtain the light source regulation index, so as to achieve intelligent and precise adjustment of the light source. Thus, it can adjust the light source in real time during night driving, and then ensure that the adjusted sightseeing vehicle headlights match the driver's needs and preferences. Moreover, it can utilize the adjustment ability of the headlights to avoid excessive or insufficient light source brightness, improve energy efficiency and service life, and at the same time ensure the best effect of the interior atmosphere light during night driving.

[0019] (4) The light source adjustment system integrates multiple modules to obtain and analyze vehicle condition data, driver facial image data, and historical light source data in real time, so as to be able to conduct comprehensive light source adjustment. It can automatically optimize the light source adjustment according to the driver's emotional changes and vehicle conditions, and then achieve more flexible and precise light source adjustment. Moreover, it can avoid unnecessary energy waste, and at the same time ensure that the headlights can provide the best lighting effect in any situation, thereby improving the accuracy and adaptability of the system and enhancing driving comfort.

[0020] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of a light source adjustment method of the present invention.

[0022] Figure 2 It is a detailed flowchart of the steps to obtain the vehicle condition adjustment index of the sightseeing vehicle headlights to be adjusted in a light source adjustment method of the present invention.

[0023] Figure 3 It is a block diagram of a light source adjustment system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Please refer to Figure 1, an embodiment of the present invention provides a technical solution: a method for adjusting a light source, including the following steps: (when driving at night) obtaining in real time the light source adjustment data of the landscape car lights to be adjusted (i.e., the in-vehicle atmosphere lights), where the light source adjustment data includes vehicle condition data and driving facial image data; performing data adjustment analysis on the light source adjustment data of the landscape car lights to be adjusted respectively to obtain the vehicle condition adjustment index and the emotion response adjustment index of the landscape car lights to be adjusted; at the same time, obtaining the historical light source data of several previous settings of the landscape car lights to be adjusted, and analyzing to obtain the preference adjustment index of the landscape car lights to be adjusted, and combining the vehicle condition adjustment index and the emotion response adjustment index of the landscape car lights to be adjusted for comprehensive regulation analysis to obtain the light source regulation index of the landscape car lights to be adjusted; and performing intelligent light source adjustment based on the light source regulation index of the landscape car lights to be adjusted.

[0025] The specific formula for calculating the light source regulation index of the landscape car lights to be adjusted is as follows: ; where is the light source regulation index of the landscape car lights to be adjusted, is the vehicle condition adjustment index of the landscape car lights to be adjusted, is the vehicle condition adjustment coefficient in the database, is the emotion response adjustment index of the landscape car lights to be adjusted, is the emotion adjustment coefficient in the database, is the preference adjustment index of the landscape car lights to be adjusted, is the preference adjustment coefficient in the database, is the gain adjustment coefficient in the database, is the composite adjustment coefficient in the database.

[0026] It should be noted that the item in the formula is used to adjust the interaction between the vehicle condition adjustment index and the emotion response adjustment index to avoid the light source regulation index being too high or too low.

[0027] , , , , can be obtained through the following steps: using historical data, combining the vehicle condition adjustment index, the emotion response adjustment index, and the preference adjustment index, performing statistical regression analysis to quantify the specific impact of each factor on the light source regulation index, thereby fitting the initial weight values. Secondly, using the sensitivity analysis method, adjusting the value range of each coefficient and observing its impact on the light source regulation evaluation result to ensure the stability and rationality of the model.

[0028] Specifically, such as Figure 2As shown, the vehicle condition data includes the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index. The specific steps to obtain the vehicle condition adjustment index of the landscape lamp to be adjusted are as follows: comprehensively analyze the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index of the landscape lamp to be adjusted to obtain the in-vehicle light environment adjustment index of the landscape lamp to be adjusted; obtain the driving speed adjustment index, the steering adjustment index, and the external light intensity value of the landscape lamp to be adjusted, and perform normalization processing with the in-vehicle light environment adjustment index; based on the normalized driving speed adjustment index, steering adjustment index, external light intensity value, and in-vehicle light environment adjustment index of the landscape lamp to be adjusted, conduct comprehensive analysis to obtain the vehicle condition adjustment index of the landscape lamp to be adjusted.

[0029] Among them, the interior reflection index is the comprehensive light reflection ability of the surface of each interior material in the vehicle (such as leather, wood, metal, etc.). It can be obtained by obtaining the reflectivity of each interior material and performing weighted processing. The obtained result is this parameter, and the reflectivity of each interior material can be obtained from the optical material data table stored in the database.

[0030] The interior light absorption index is the comprehensive light absorption ability of the surface of each interior material in the vehicle (such as leather, wood, metal, etc.). It can be obtained by obtaining the light absorption value of each interior material and performing weighted processing. The obtained result is this parameter, and the light absorption value of each interior material can be obtained from the optical material data table stored in the database.

[0031] The in-vehicle environment adjustment index is the comprehensive influence of the in-vehicle environment on the adjustment of the in-vehicle atmosphere lamp. It can be obtained by obtaining the in-vehicle temperature value (which can be obtained through the in-vehicle temperature sensor), the in-vehicle humidity value (which can be obtained through the in-vehicle humidity sensor), the in-vehicle light intensity value (which can be obtained through the in-vehicle light sensor), the in-vehicle noise value (which can be obtained through the in-vehicle noise sensor), the in-vehicle temperature reference value, the in-vehicle humidity reference value, the in-vehicle light intensity reference value, and the in-vehicle noise reference value, and respectively performing ratio processing (such as the absolute value of the difference between the in-vehicle temperature value and the in-vehicle temperature reference value / the in-vehicle temperature reference value), and performing weighted processing based on the ratio processing result. The obtained result is this parameter, and the in-vehicle temperature reference value can be obtained by obtaining the historical in-vehicle temperature values of several times and performing mean processing. The acquisition logics of the in-vehicle humidity reference value, the in-vehicle light intensity reference value, and the in-vehicle noise reference value are the same as that of the in-vehicle temperature reference value.

[0032] The driving speed adjustment index is used to evaluate the impact of driving speed on the adjustment of the in-vehicle ambient light source. At higher vehicle speeds, the brightness of the in-vehicle ambient light decreases to avoid disturbing the driver's line of sight. Conversely, at lower vehicle speeds, the brightness of the in-vehicle ambient light needs to be increased to enhance comfort. This can be achieved by obtaining the driving speed value (which can be obtained through a speed sensor), the driving speed reference value (i.e., the speed limit of the current driving road, which can be obtained through GPS navigation), and performing a ratio analysis. The result obtained is this parameter, i.e., |driving speed value - driving speed reference value| / driving speed reference value.

[0033] The steering adjustment index is used to evaluate the impact of vehicle steering operations on the adjustment of the in-vehicle ambient light source. When turning, the in-vehicle ambient light needs to be adjusted to ensure the comfort of the vehicle owner. This can be achieved by obtaining the steering angle value (which can be obtained through a steering angle sensor), the steering angular velocity value (which can be obtained through a gyroscope), and performing a normalization process, and then performing a weighted process based on the normalization result. The result obtained is this parameter.

[0034] The external light intensity value can be obtained through an external light sensor outside the vehicle.

[0035] The specific formulas for calculating the in-vehicle light environment adjustment index and vehicle condition adjustment index of the landscape lights to be adjusted are as follows: ; where is the in-vehicle light environment adjustment index of the landscape lights to be adjusted, is the in-vehicle environment adjustment index of the landscape lights to be adjusted, is the in-vehicle environment adjustment coefficient stored in the database, is the interior reflection index of the landscape lights to be adjusted, is the interior reflection adjustment coefficient stored in the database, is the interior light absorption index of the landscape lights to be adjusted, is the interior light absorption adjustment coefficient stored in the database, is the interaction adjustment coefficient stored in the database, is the difference adjustment coefficient stored in the database, is the vehicle condition adjustment index of the landscape lights to be adjusted, is the driving speed adjustment index of the landscape lights to be adjusted after normalization, is the speed adjustment coefficient stored in the database, is the external light intensity value of the landscape lights to be adjusted after normalization, is the external light adjustment coefficient stored in the database, is the steering adjustment index of the landscape lights to be adjusted after normalization, is the steering adjustment coefficient stored in the database, is the in-vehicle light environment adjustment index of the landscape lights to be adjusted after normalization, is the internal and external difference adjustment coefficient stored in the database.

[0036] It should be noted that this term is used to quantify the relative difference between the interior reflection index and the interior light absorption index, ensuring appropriate adjustment effects under different interior materials.

[0037] and and and and can be obtained through the following steps: Based on historical data, combined with the in-vehicle environment adjustment index, interior reflection index, and interior light absorption index, perform statistical regression analysis to quantify the specific impact of each factor on the in-vehicle light environment adjustment index, thereby fitting the initial weight values. Secondly, use the sensitivity analysis method to adjust the value range of each coefficient and observe its impact on the evaluation results of the in-vehicle light environment adjustment to ensure the stability and rationality of the model.

[0038] In the formula this term is used to adjust the differential impact between the external light intensity value and the in-vehicle light environment adjustment index.

[0039] and and and can be obtained through the following steps: Based on historical data, determine the initial impact weights of each variable (such as driving speed adjustment index, external light intensity value, steering adjustment index, in-vehicle light environment adjustment index) on the vehicle condition adjustment index through statistical regression analysis. Then, use the sensitivity analysis method to adjust the value range of the coefficients to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as machine learning algorithms) to ensure that the formula can accurately reflect the impact of vehicle conditions on light source adjustment.

[0040] The specific implementation of calculating the vehicle condition adjustment index of the landscape lamp to be adjusted is as follows. The following data is available: The in-vehicle environment adjustment index of the landscape lamp to be adjusted is approximately: 0.305.

[0041] The interior reflection index of the landscape lamp to be adjusted is approximately: 0.295.

[0042] The interior light absorption index of the landscape lamp to be adjusted is approximately: 0.669.

[0043] The internal environment adjustment coefficient stored in the database is approximately: 0.412.

[0044] The interior reflection adjustment coefficient stored in the database is approximately: 1.548.

[0045] The light absorption adjustment coefficient stored in the database is approximately: 0.247.

[0046] The interaction adjustment coefficient stored in the database is approximately: 0.318.

[0047] The difference adjustment coefficient stored in the database is approximately: 1.426.

[0048] Substitute the above data into the specific formula for calculating the in-vehicle light environment adjustment index of the landscape vehicle lamp to be adjusted, and we get: The in-vehicle light environment adjustment index of the landscape vehicle lamp to be adjusted ≈ 0.818.

[0049] And the driving speed adjustment index of the landscape vehicle lamp to be adjusted is approximately: 0.217.

[0050] The steering adjustment index of the landscape vehicle lamp to be adjusted is approximately: 0.364.

[0051] The external light intensity value of the landscape vehicle lamp to be adjusted is approximately (unit: ux): 83.000.

[0052] And perform normalization processing to get: The in-vehicle light environment adjustment index of the landscape vehicle lamp to be adjusted after normalization is approximately: 0.726.

[0053] The driving speed adjustment index of the landscape vehicle lamp to be adjusted after normalization is approximately: 0.371.

[0054] The steering adjustment index of the landscape vehicle lamp to be adjusted after normalization is approximately: 0.416.

[0055] The external light intensity value of the landscape vehicle lamp to be adjusted after normalization is approximately: 0.467.

[0056] The speed adjustment coefficient stored in the database is approximately: 0.197.

[0057] The external light adjustment coefficient stored in the database is approximately: 0.327.

[0058] The steering adjustment coefficient stored in the database is approximately: 0.241.

[0059] The internal and external difference adjustment coefficient stored in the database is approximately: 0.683.

[0060] And substitute the above data into the specific formula for calculating the vehicle condition adjustment index of the landscape vehicle lamp to be adjusted, and we get: The vehicle condition adjustment index of the landscape vehicle lamp to be adjusted ≈ 0.881.

[0061] In this implementation scheme, through the comprehensive analysis of the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index, it is possible to comprehensively evaluate the influence of different interior materials and environmental factors (such as temperature, humidity, noise, etc.) in the vehicle on the adjustment of the in-vehicle light source. Thus, it ensures that in different in-vehicle environments, the light source of the landscape vehicle can be precisely adjusted according to specific needs, thereby providing the best lighting effect for the driver and avoiding the light source imbalance caused by interior materials or environmental factors. Secondly, by obtaining dynamic driving data such as driving speed, steering angle, and external light intensity, and performing normalization processing with the in-vehicle light environment adjustment index, it is possible to adjust the vehicle light source in real time according to changes in driving conditions. For example, when driving at high speed, the light source brightness will automatically decrease to reduce interference with the driver's line of sight, while when driving at low speed or turning, the light source will increase to provide more comfort and a sense of security. Finally, through statistical regression analysis and sensitivity analysis, it is possible to precisely quantify the influence of the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index on the light source adjustment, and adjust each parameter coefficient to ensure that the light source adjustment is more personalized, stable, and reasonable. In addition, combining machine learning algorithms to optimize the model and automatically adapting to different vehicle conditions and driving environments according to historical data, and adjusting the light source in real time to further improve intelligence and adaptability, thereby ensuring the best light source adjustment effect in various driving scenarios.

[0062] Specifically, the driving facial image data is specifically the pixel value and two-dimensional coordinates of each pixel point in the driving facial image, and the specific steps to obtain the emotion response adjustment index of the landscape vehicle light to be adjusted are as follows: Input the pixel value and two-dimensional coordinates of each pixel point in the driving facial image of the landscape vehicle light to be adjusted into a pre-trained facial expression recognition model for predictive analysis to obtain the emotion feedback set of the landscape vehicle light to be adjusted, that is, the emotion perception index (measuring the current emotion intensity state of the driver), the emotion reaction sensitivity index (measuring the reaction intensity of the driver to the light change), and the emotion adaptation index (measuring the matching degree between the current in-vehicle light effect and the driver's facial emotion reaction); and perform a comprehensive analysis on the emotion perception index, the emotion reaction sensitivity index, and the emotion adaptation index of the landscape vehicle light to be adjusted to obtain the emotion response adjustment index of the landscape vehicle light to be adjusted.

[0063] The specific formula for calculating the emotion response adjustment index of the landscape vehicle light to be adjusted is as follows: ; where is the emotion response adjustment index of the landscape vehicle light to be adjusted, is the emotion perception index of the landscape vehicle light to be adjusted, is the perception coefficient stored in the database, is the perception adjustment coefficient stored in the database, is the emotion reaction sensitivity index of the landscape vehicle light to be adjusted, is the sensitivity index stored in the database, is the sensitivity adjustment index stored in the database, is the emotional adaptation index of the landscape car light to be adjusted, is the adaptation coefficient stored in the database, is the adaptation adjustment index stored in the database, is the superposition adjustment index stored in the database, .

[0064] It should be noted that in the formula, this term is used to adjust the superposition effect of the emotional perception index, emotional response sensitivity index, and emotional adaptation index, to avoid the emotional response adjustment index being too high or too low.

[0065] , , can be obtained through the following steps: read the emotional perception index, emotional response sensitivity index, and emotional adaptation index of the landscape car light to be adjusted, and perform a summation analysis to obtain the emotional sum value, and then perform a ratio analysis of the emotional perception index, emotional response sensitivity index, and emotional adaptation index of the landscape car light to be adjusted with the emotional sum value respectively, and take the corresponding coefficients for the ratio analysis results.

[0066] , , , can be obtained through the following steps: based on historical data, determine the initial influence weights of each variable (emotional perception index, emotional response sensitivity index, emotional adaptation index) on the vehicle condition adjustment index through statistical regression analysis, and then use the sensitivity analysis method to adjust the value range of the coefficient to evaluate the stability and applicability of these parameters to the formula output. Next, further fit the weights through model optimization (such as multi-objective optimization) to ensure that the formula can accurately reflect the influence of vehicle conditions on light source adjustment.

[0067] In this implementation, the pixel values and two-dimensional coordinates of each pixel point in the facial image are input into the emotion recognition model to analyze in real time the emotion intensity of the driver, the reaction intensity to light source changes, and the matching degree between the current in-vehicle light environment and the driver's emotion. Thereby, the light source of the in-vehicle landscape lights can be dynamically adjusted according to the driver's emotional state, so as to enhance the driving experience and reduce the impact of emotional fluctuations on driving. Secondly, the comprehensive analysis of the emotion perception index, emotion reaction sensitivity index, and emotion adaptation index enables the light source adjustment not to rely solely on static parameters, but to be flexibly adjusted according to the driver's immediate emotional reaction, thereby improving the driver's comfort, reducing visual discomfort or fatigue caused by emotional mismatch, and then enhancing the quality of the driving experience. Finally, through methods such as sensitivity analysis and multi-objective optimization, the coefficients of the emotion perception index, reaction sensitivity index, and adaptation index can be optimized to ensure that the formula can work stably in various driving environments, and thus the light source adjustment can be accurately adapted to different emotional states, avoiding over-adjustment or under-adjustment of the emotion response, and then ensuring the rationality and stability of the vehicle light source adjustment while the emotion changes.

[0068] Specifically, the facial expression recognition model is specifically a deep convolutional neural network. The deep convolutional neural network includes an input layer, several convolutional layers, a non-linear activation layer, a pooling layer, a flattening layer, a fully-connected layer, and a regression output layer. The specific steps to obtain the emotional feedback set of the landscape vehicle lamp to be adjusted are as follows: In the input layer of the deep convolutional neural network, the driving facial image data of the landscape vehicle lamp to be adjusted is received and preprocessed; in the convolutional layer of the deep convolutional neural network, feature extraction processing is performed on the preprocessed driving facial image data of the landscape vehicle lamp to be adjusted (that is, by sliding a convolutional kernel, such as a filter, to scan the input image data, and different levels of features are extracted from the image, such as the shape of the mouth, the degree of eye closure, etc., and a feature map is generated), to obtain the facial feature map of the landscape vehicle lamp to be adjusted; in the non-linear activation layer of the deep convolutional neural network, non-linear activation processing is performed on the facial feature map of the landscape vehicle lamp to be adjusted (that is, non-linear factors are introduced to enable the network to learn more complex features, such as the ReLU activation function performing non-linear processing on the convolutional output); in the pooling layer of the deep convolutional neural network, dimensionality reduction processing is performed on the facial feature map of the landscape vehicle lamp to be adjusted after non-linear activation processing (that is, the most representative part is selected from the activated feature map, such as the maximum value or average value of a local area, to reduce its dimension and spatial resolution, reduce the computational amount, and at the same time retain important spatial information), to obtain the facial dimensionality-reduced feature map of the landscape vehicle lamp to be adjusted; in the flattening layer of the deep convolutional neural network, flattening processing is performed on the facial dimensionality-reduced feature map of the landscape vehicle lamp to be adjusted (that is, the two-dimensional matrix of each channel in the feature map is flattened into a one-dimensional vector, and the flattening results of all channels are connected. For the flattening result of each channel, a one-dimensional vector will be obtained, and finally these vectors are merged into a longer one-dimensional vector), to obtain the facial feature vector of the landscape vehicle lamp to be adjusted; in the fully-connected layer of the deep convolutional neural network, feature fusion processing is performed on the facial feature vector of the landscape vehicle lamp to be adjusted (that is, processing with a weight matrix and an activation function. There will be a weight between each input neuron and the output neuron, and the input features are fused through weighted summation and non-linear activation is performed to increase the non-linear ability of the model, to obtain complex features), to obtain the facial complex feature vector (that is, the high-level feature vector) of the landscape vehicle lamp to be adjusted.In the regression output layer of the deep convolutional neural network, regression prediction analysis is performed on the facial feature vector of the landscape vehicle lamp to be adjusted (that is, each regression branch is responsible for predicting a different index, and each regression branch is independent and can make predictions based on the input shared facial feature vector. The regression branch of each task will further process the complex facial feature vector through a fully connected layer, map the complex facial feature vector to a new space, and calculate the corresponding index through linear combination, such as the emotion perception index. Matrix multiplication is performed on the input complex facial feature vector and the weight matrix, and a bias term is added at the same time, and then the output is obtained through a linear activation function, and the output value is between 0 and 1), obtaining the emotion perception index, emotion response sensitivity index, and emotion adaptation index of the landscape vehicle lamp to be adjusted, that is, the emotion feedback set.

[0069] Among them, the input layer is used to receive the driving facial image data of the landscape vehicle lamp to be adjusted. What is input is the pixel value and two-dimensional coordinate data of each pixel point. These data will be used as the input of the model and passed to the convolutional layer for processing. The goal of the input layer is to perform preliminary preprocessing on the input image, such as normalization (ensuring that the data range is suitable for network learning).

[0070] The convolutional layer is used for feature extraction. The convolutional layer will extract local features related to facial expressions, such as the shape of the mouth, the degree of eye closure, etc. These low-level features provide a basis for subsequent emotion prediction.

[0071] The non-linear activation layer is used to transform the features extracted by the convolutional layer into non-linear feature maps through an activation function, so that the model can learn more complex mappings and capture the complex relationship between facial expressions and emotions.

[0072] The pooling layer is used to reduce the dimension of the feature map and retain the most important features, such as retaining important information in facial expressions (such as the height of the eyebrows, the upward curvature of the corners of the mouth, etc.) and removing unimportant details.

[0073] The flattening layer is used to flatten the facial reduced-dimensional feature map into a one-dimensional vector, compressing the features of each pixel into a column of numerical values. This one-dimensional vector contains all the feature information extracted from the image and provides input for the fully connected layer.

[0074] The fully connected layer is used to perform weighted sum on the output of the flattening layer to form the final complex facial feature vector. This complex facial feature vector integrates all the information from each layer (such as emotion intensity, facial features, expression changes, etc.).

[0075] The regression output layer is used to perform regression analysis and make predictions on the complex facial feature vector, outputting the emotion perception index, emotion response sensitivity index, emotion adaptation index, etc.

[0076] And the pre-training steps of the deep convolutional neural network are as follows: Obtain an image annotation dataset, which contains several sets of face annotation images of emotional states (such as happy, sad, angry, surprised, etc.), and divide the image annotation dataset into a face training set and a face validation set.

[0077] Initialize the convolutional neural network by initializing the weights and biases in the network to ensure that the network can effectively learn features. Initialize the weights of the convolutional layer (using He initialization), initialize the biases (initialize the bias terms to zero), and use the ReLU activation function to increase the non-linearity of the network.

[0078] Train based on the face training set, that is, set the number of training loops, and in each training loop, update the weights of the network through the backpropagation algorithm.

[0079] And the processing steps for each training loop: Forward propagation: Process each input image through the layers of the network (convolutional layer, pooling layer, fully connected layer) to obtain the predicted values of the model.

[0080] Calculate the loss: Calculate the value of the loss function based on the difference between the prediction results and the true labels.

[0081] Backpropagation: Through the backpropagation algorithm, calculate the gradients of the loss function with respect to the weights of each layer, and update the parameters of the model based on these gradients. Backpropagation uses the chain rule to propagate the error from the output layer back to the input layer and updates the weights according to the gradients.

[0082] After each training loop, conduct an evaluation and analysis based on the face validation set. Adjust the model structure or hyperparameters, such as the learning rate, by calculating the error of the validation set. Select a suitable learning rate. An overly large learning rate may lead to unstable training, and an overly small learning rate may lead to a too slow convergence rate. A dynamic learning rate adjustment strategy or an adaptive learning rate method can be used.

[0083] If the error of the face validation set is high while the error of the face training set is low, it may be overfitting, and regularization methods (such as L2 regularization or Dropout) can be adopted to reduce overfitting.

[0084] If the performance of the model does not meet the expectations, try to adjust the network structure (increase / decrease the number of layers), optimization algorithm, data augmentation method, etc. to further improve the performance of the model.

[0085] When the training is completed and the loss and accuracy on the face validation set reach the expected standards, the training process ends, and a trained network model is obtained.

[0086] In this implementation scheme, the deep convolutional neural network can deeply analyze the changes in facial expressions by performing multi-layer processing (such as feature extraction, non-linear activation, pooling, etc.) on the driver's facial image data, so as to accurately capture subtle emotional fluctuations such as emotional intensity, reaction sensitivity, and adaptability. Thus, it can adjust the in-vehicle light source in real time based on the driver's emotional state, enhance the driving experience, and then avoid the discomfort caused by emotional disorders. Secondly, through the predictive analysis of the regression output layer, accurate adjustments can be made for different emotional states, so that the in-vehicle light source can maintain a good match with the driver's emotional reactions. Finally, through the multi-layer processing of the deep convolutional neural network, the facial features of the driver can be comprehensively analyzed, and then personalized light source adjustment can be provided for each driver. Consequently, during driving, the changes in the vehicle lights will not have an adverse impact on the driver's emotions, but will provide appropriate lighting according to the driver's needs and emotions, thereby enhancing driving safety and comfort, which is particularly important during night driving. In addition, through a systematic training process (including forward propagation, loss calculation, backpropagation, etc.), combined with facial expression data, the network model can be continuously optimized, and finally accurate identification and prediction of the driver's emotions can be achieved.

[0087] Specifically, the historical light source data includes historical brightness values, historical color temperature values, historical hue values, historical light source saturation values, and historical gradient speed values. The specific steps to obtain the preference adjustment index of the landscape vehicle light to be adjusted are as follows: comprehensively analyze (i.e., standard deviation processing) the historical brightness values, historical color temperature values, historical hue values, historical light source saturation values, and historical gradient speed values of each historical setting of the landscape vehicle light to be adjusted, to obtain the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle light to be adjusted, and perform standardization processing (i.e., unit removal processing); and comprehensively analyze the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle light to be adjusted after standardization processing, to obtain the preference adjustment index of the landscape vehicle light to be adjusted.

[0088] Among them, the historical brightness values, historical color temperature values, historical hue values, historical light source saturation values, and historical gradient speed values can all be obtained through the vehicle data recorder.

[0089] The specific formula for calculating the preference adjustment index of the landscape vehicle light to be adjusted is as follows: ; where is the preference adjustment index of the landscape vehicle light to be adjusted, is the historical brightness fluctuation index of the landscape vehicle light to be adjusted after standardization processing, is the brightness coefficient in the database, is the historical color temperature fluctuation index of the landscape car light to be adjusted after standardization, is the color temperature coefficient in the database, is the historical hue fluctuation index of the landscape car light to be adjusted after standardization, is the hue coefficient in the database, is the historical light source saturation fluctuation index of the landscape car light to be adjusted after standardization, is the saturation coefficient in the database, is the historical gradient speed fluctuation index of the landscape car light to be adjusted after standardization, is the gradient coefficient in the database, , is the natural constant, and its value is 2.71 in this embodiment.

[0090] It should be noted that, , , , , can be obtained through the following steps: read the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape car light to be adjusted after standardization, and perform summation analysis to obtain the preference sum value, and perform ratio analysis on the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape car light to be adjusted after standardization with the preference sum value respectively, and use the ratio analysis results as the corresponding parameters.

[0091] In this implementation plan, through the fluctuation analysis of multiple light source parameters such as historical brightness, color temperature, hue, saturation, and gradient speed, it is possible to quantify and identify the driver's preference degree for these parameters, so as to provide the light source adjustment plan that best meets the driver's needs based on historical data, thereby ensuring the comfort and adaptability of the car lights in different driving scenarios and improving the driver's satisfaction. Secondly, through the standard deviation processing and standardization processing of historical light source data, it is possible to eliminate the dimension difference of different light source parameters and accurately reflect the volatility of each light source parameter under different driving conditions, so as to deeply analyze the driver's acceptance of light source changes, thereby ensuring that the adjustment of the car lights is more in line with personal preferences, avoiding overly drastic or inappropriate light source changes, and improving comfort. Finally, by collecting and analyzing historical data, it not only provides personalized adjustment for the current driving environment, but also can optimize the system by continuously accumulating data, so that in future driving processes, it is possible to further accurately adjust the light source based on more historical data, thereby better meeting the driver's changing needs and improving the long-term adaptability and accuracy of light source adjustment.

[0092] Specifically, the specific steps for intelligent light source adjustment based on the light source control index of the landscape vehicle lamp to be adjusted are as follows: Judge and analyze the light source control index of the landscape vehicle lamp to be adjusted with the preset light source control index threshold; If the light source control index of the landscape vehicle lamp to be adjusted is lower than the preset light source control index threshold, a corresponding gain control signal is generated, and the landscape vehicle lamp to be adjusted is adjusted (by driving circuit) (to improve certain parameters of the vehicle lamp, such as brightness, color temperature, hue, etc., to make the light source adjustment reach a more appropriate state. For example, the brightness of the light source can be increased, or the color temperature and hue can be adjusted to make the light source of the vehicle lamp more in line with the driver's needs and driving environment); If the light source control index of the landscape vehicle lamp to be adjusted is not lower than the preset light source control index threshold, a corresponding reduction control signal is generated, and the landscape vehicle lamp to be adjusted is adjusted (by driving circuit) (to reduce certain parameters of the vehicle lamp, such as reducing brightness, lowering color temperature or adjusting hue, to avoid the light source being too dazzling or interfering with the driver's line of sight. For example, the brightness can be reduced or the color temperature can be adjusted to make the light source of the vehicle lamp more in line with the driver's comfort needs and avoid the strong light source affecting the driving experience).

[0093] In this implementation plan, by calculating and comparing the light source control index of the landscape vehicle lamp to be adjusted with the preset threshold in real time, dynamic adjustment can be made according to the current driving environment and driver's needs, so that parameters such as the brightness, color temperature and hue of the vehicle lamp can always be maintained within a most appropriate range, ensuring that the light source effect in each driving scenario meets the driver's comfort needs. For example, when driving at night, the light source brightness can be automatically increased, while in a strong light environment, the brightness can be reduced to avoid eye fatigue. And based on the intelligent light source adjustment, it can automatically adjust according to the real-time control index and preset threshold of the vehicle lamp without manual operation by the driver, thus simplifying the driver's operation steps, improving the driving convenience, enhancing the user experience, reducing human errors or inappropriate manual adjustments, and then ensuring that the light source is always in the best state under different circumstances.

[0094] Please refer to Figure 3, an embodiment of the present invention provides a technical solution: a light source adjustment system, comprising: an adjustment data acquisition module for real-time acquisition of light source adjustment data of a landscape vehicle lamp to be adjusted, the light source adjustment data including vehicle condition data and driving facial image data; an adjustment data analysis module for respectively performing data adjustment analysis on the light source adjustment data of the landscape vehicle lamp to be adjusted to obtain a vehicle condition adjustment index and an emotion response adjustment index of the landscape vehicle lamp to be adjusted; a comprehensive adjustment analysis module for simultaneously acquiring historical light source data of several previous settings of the landscape vehicle lamp to be adjusted, analyzing to obtain a preference adjustment index of the landscape vehicle lamp to be adjusted, and performing comprehensive control analysis in combination with the vehicle condition adjustment index and the emotion response adjustment index of the landscape vehicle lamp to be adjusted to obtain a light source control index of the landscape vehicle lamp to be adjusted; an intelligent light source adjustment module for performing intelligent light source adjustment based on the light source control index of the landscape vehicle lamp to be adjusted.

[0095] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0096] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for adjusting a light source, characterized in that, It includes the following steps: Obtain the light source adjustment data of the landscape car light to be adjusted in real time, where the light source adjustment data includes vehicle condition data and driving facial image data; Conduct data adjustment analysis on the light source adjustment data of the landscape car light to be adjusted respectively to obtain the vehicle condition adjustment index and the emotional response adjustment index of the landscape car light to be adjusted; Meanwhile, obtain the historical light source data of several previous settings of the landscape car light to be adjusted, analyze to obtain the preference adjustment index of the landscape car light to be adjusted, and conduct comprehensive regulation analysis in combination with the vehicle condition adjustment index and the emotional response adjustment index of the landscape car light to be adjusted to obtain the light source regulation index of the landscape car light to be adjusted; And perform intelligent light source adjustment based on the light source regulation index of the landscape car light to be adjusted.

2. The light source adjustment method according to claim 1, wherein The vehicle condition data includes the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index, and the specific steps to obtain the vehicle condition adjustment index of the landscape car light to be adjusted are as follows: Conduct comprehensive analysis on the in-vehicle environment adjustment index, the interior reflection index, and the interior light absorption index of the landscape car light to be adjusted to obtain the in-vehicle light environment adjustment index of the landscape car light to be adjusted; Obtain the driving speed adjustment index, the steering adjustment index, and the external light intensity value of the landscape car light to be adjusted, and perform normalization processing with the in-vehicle light environment adjustment index; Based on the comprehensively analyzed driving speed adjustment index, steering adjustment index, external light intensity value, and in-vehicle light environment adjustment index of the landscape car light to be adjusted after normalization processing, obtain the vehicle condition adjustment index of the landscape car light to be adjusted.

3. The light source adjustment method according to claim 2, characterized in that The specific formula for calculating the vehicle condition adjustment index of the landscape vehicle lamp to be adjusted is as follows: ; Among them, is the vehicle condition adjustment index of the landscape car light to be adjusted, , , , are successively the driving speed adjustment index, external light intensity value, steering adjustment index, and in-vehicle light environment adjustment index of the landscape car light to be adjusted after normalization processing, , , , are successively the speed adjustment coefficient, external light adjustment coefficient, steering adjustment coefficient, and internal-external difference adjustment coefficient stored in the database.

4. The light source adjustment method according to claim 1, characterized in that The driving facial image data is specifically the pixel value and two-dimensional coordinate of each pixel point in the driving facial image, and the specific steps to obtain the emotional response adjustment index of the landscape car light to be adjusted are as follows: Input the pixel value and two-dimensional coordinate of each pixel point in the driving facial image of the landscape car light to be adjusted into a pre-trained facial expression recognition model for prediction analysis to obtain the emotional feedback set of the landscape car light to be adjusted, namely the emotional perception index, the emotional reaction sensitivity index, and the emotional adaptation index; And conduct comprehensive analysis on the emotional perception index, the emotional reaction sensitivity index, and the emotional adaptation index of the landscape car light to be adjusted to obtain the emotional response adjustment index of the landscape car light to be adjusted.

5. The light source adjustment method according to claim 4, wherein The specific formula for calculating the emotional response adjustment index of the landscape car lights to be adjusted is as follows: ; Among them, is the emotional response adjustment index of the landscape car light to be adjusted, , , are successively the emotional perception index, emotional response sensitivity index, and emotional adaptation index of the landscape car light to be adjusted, , , , , , , are successively the perception coefficient, perception adjustment coefficient, reaction sensitivity index, reaction sensitivity adjustment index, adaptation coefficient, adaptation adjustment index, and superposition adjustment index stored in the database, .

6. The light source adjustment method according to claim 4, wherein The facial expression recognition model is specifically a deep convolutional neural network, and the deep convolutional neural network includes an input layer, several convolutional layers, a non-linear activation layer, a pooling layer, a flattening layer, a fully connected layer, and a regression output layer. The specific steps to obtain the emotional feedback set of the landscape car light to be adjusted are as follows: In the input layer of the deep convolutional neural network, receive the driving facial image data of the landscape car light to be adjusted and perform preprocessing; In the convolutional layer of the deep convolutional neural network, perform feature extraction processing on the preprocessed driving facial image data of the landscape car light to be adjusted to obtain the facial feature map of the landscape car light to be adjusted; In the non-linear activation layer of the deep convolutional neural network, perform non-linear activation processing on the facial feature map of the landscape car light to be adjusted; In the pooling layer of the deep convolutional neural network, perform dimensionality reduction processing on the non-linearly activated facial feature map of the landscape car light to be adjusted to obtain the facial dimensionality reduction feature map of the landscape car light to be adjusted; In the flattening layer of the deep convolutional neural network, the face dimensionality reduction feature map of the landscape vehicle lamp to be adjusted is flattened to obtain the face feature vector of the landscape vehicle lamp to be adjusted; In the fully connected layer of the deep convolutional neural network, the face feature vector of the landscape vehicle lamp to be adjusted is subjected to feature fusion processing to obtain the face complex feature vector of the landscape vehicle lamp to be adjusted; In the regression output layer of the deep convolutional neural network, regression prediction analysis is performed on the face feature vector of the landscape vehicle lamp to be adjusted to obtain the emotion perception index, emotion response sensitivity index, and emotion adaptation index of the landscape vehicle lamp to be adjusted, that is, the emotion feedback set.

7. The light source adjustment method according to claim 1, wherein The historical light source data includes historical brightness value, historical color temperature value, historical hue value, historical light source saturation value, and historical gradient speed value, and the specific steps to obtain the preference adjustment index of the landscape vehicle lamp to be adjusted are as follows: Comprehensively analyze the historical brightness value, historical color temperature value, historical hue value, historical light source saturation value, and historical gradient speed value set for the landscape vehicle lamp to be adjusted each time in history to obtain the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle lamp to be adjusted, and perform standardization processing; And comprehensively analyze the historical brightness fluctuation index, historical color temperature fluctuation index, historical hue fluctuation index, historical light source saturation fluctuation index, and historical gradient speed fluctuation index of the landscape vehicle lamp to be adjusted after the standardization processing to obtain the preference adjustment index of the landscape vehicle lamp to be adjusted.

8. The light source adjustment method according to claim 1, wherein The specific formula for calculating the light source regulation index of the landscape car lamp to be adjusted is as follows: ; Among them, is the light source regulation index of the landscape car light to be adjusted, , , are successively the vehicle condition adjustment index, the emotion response adjustment index, and the preference adjustment index of the landscape car light to be adjusted, , , , , are successively the vehicle condition adjustment coefficient, the emotion adjustment coefficient, the preference adjustment coefficient, the gain adjustment coefficient, and the composite adjustment coefficient in the database.

9. The light source adjustment method according to claim 1, wherein The specific steps for intelligent light source adjustment based on the light source control index of the landscape vehicle lamp to be adjusted are as follows: Perform judgment analysis on the light source control index of the landscape vehicle lamp to be adjusted and the preset light source control index threshold; If the light source control index of the landscape vehicle lamp to be adjusted is lower than the preset light source control index threshold, generate a corresponding gain control signal and adjust the landscape vehicle lamp to be adjusted; If the light source control index of the landscape vehicle lamp to be adjusted is not lower than the preset light source control index threshold, generate a corresponding reduction control signal and adjust the landscape vehicle lamp to be adjusted.

10. A light source adjustment system applying the light source adjustment method according to any one of claims 1-9, characterized in that, Including: An adjustment data acquisition module for real-time acquisition of the light source adjustment data of the landscape vehicle lamp to be adjusted, where the light source adjustment data includes vehicle condition data and driving face image data; An adjustment data analysis module for performing data adjustment analysis on the light source adjustment data of the landscape vehicle lamp to be adjusted respectively to obtain the vehicle condition adjustment index and emotion response adjustment index of the landscape vehicle lamp to be adjusted; A comprehensive adjustment analysis module for simultaneously acquiring the historical light source data of the landscape vehicle lamp to be adjusted set in a number of historical times, analyzing to obtain the preference adjustment index of the landscape vehicle lamp to be adjusted, and performing comprehensive control analysis in combination with the vehicle condition adjustment index and emotion response adjustment index of the landscape vehicle lamp to be adjusted to obtain the light source control index of the landscape vehicle lamp to be adjusted; An intelligent light source adjustment module for performing intelligent light source adjustment based on the light source control index of the landscape vehicle lamp to be adjusted.

Images