Vehicle machine system screen brightness self-adaptive adjustment method considering driver characteristics

Abstract

The invention discloses an in-vehicle infotainment system screen brightness adaptive adjustment method considering driver characteristics, comprising the following steps: step 1, acquiring ambient light intensity data under four different scenes, and preprocessing the light intensity data to obtain a first data set; 2, collecting a face image of a driver while collecting light intensity data, and extracting characteristics of the driver from the face image to obtain a second data set; 3, respectively recording the screen brightness corresponding to the four different scenes when the opening degree of the eyes before and after the driver watches the screen is minimum; 4, establishing a mapping model of the screen brightness based on the age of the driver on the basis of the first data set, the second data set and the screen brightness, and constructing a screen brightness function based on the characteristics of the driver; and 5, dynamically adjusting the screen brightness function in the step 4 in combination with the change rate of the opening degree of the eyes of the driver. The method better meets the requirements of different drivers for the screen brightness.

Description

Technical Field

[0001] The present invention relates to the technical field of human-computer interaction, and in particular to a method for adaptively adjusting screen brightness of a vehicle computer system taking into account driver characteristics. Background Art

[0002] At present, the adaptive adjustment of the screen brightness of the car system is a very mature technology. This technology automatically adjusts the screen brightness according to the ambient light to improve comfort and driving safety. However, in actual use, since different drivers have different visual preferences and visual conditions, the screen brightness adjustment strategy that only considers ambient light can only meet the needs of a small number of drivers. For some drivers, they may feel that the screen brightness is too high, and the driver may be disturbed by glare, thereby reducing driving safety; on the contrary, some people feel that the screen brightness is too low, and the driver may not be able to see the screen content clearly, which will cause certain obstacles to human-computer interaction.

[0003] In view of this, the inventor provides a method for adaptively adjusting the screen brightness of a vehicle system taking into account the characteristics of the driver, so as to solve the above technical problems. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and to propose a method for adaptively adjusting the screen brightness of a vehicle system taking into account the characteristics of the driver. This method, on the basis of traditional vehicle screen brightness adjustment, considers adaptive adjustment of the screen brightness in four different scenarios and based on the characteristics of the driver. This adjustment method is more in line with the needs of different drivers for screen brightness.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides a method for adaptively adjusting screen brightness of a vehicle system taking into account the characteristics of a driver, comprising the following steps:

[0007] Step 1: Collecting ambient light intensity data under four different scenarios, and preprocessing the light intensity data to obtain a first data set;

[0008] Step 2: While collecting the light intensity data, collect the driver's facial image, and extract the driver's characteristics from the facial image, wherein the driver's characteristics include gender, age, and eye opening degree, to obtain a second data set;

[0009] Step 3, corresponding to four different scenarios, respectively record the screen brightness when the change in the degree of eye opening and closing of the driver's eyes is the smallest before and after he or she looks at the screen;

[0010] Step 4: establishing a mapping model of screen brightness based on the driver's age based on the first data set, the second data set and the screen brightness obtained in step 3, and combining the mapping model with gender to construct a screen brightness function based on the driver's characteristics;

[0011] Step 5: Obtain the real-time opening and closing degree of the driver's eyes, and obtain the rate of change of the eye opening and closing degree. Based on the rate of change of the eye opening and closing degree, dynamically adjust the screen brightness function in step 4 to obtain the target screen brightness that takes into account the driver's characteristics.

[0012] Furthermore, in step 1, ambient light intensity data in four different scenarios are collected by a photosensitive sensor or a camera; the preprocessing is to clean the light intensity data.

[0013] Further, in step 1, the four different scenarios include the driver driving during the day, driving at night, driving from dusk to night, and driving from dawn to early morning.

[0014] Furthermore, in step 2, the driver's facial image is captured by a camera, and the driver's characteristics are extracted from the driver's facial image using a deep learning method.

[0015] Further, step 4 includes the following steps:

[0016] Step 4.1, dividing the data in the first data set, the second data set and the screen brightness L into four groups of data packets according to four different scenarios, each group of the data packets includes light intensity I, eye opening degree E and screen brightness L;

[0017] Step 4.2: Use a quadratic polynomial to establish a regression model for the light intensity I, eye opening degree E, and screen brightness L of each group of data packets in step 4.1. The quadratic polynomial regression model is:

[0018] E=β 0 +β 1 I+β 2 L+β 3 ·(I·L)+β 4 I 2 +β 5 ·L 2 (1);

[0019] Among them, β i (i=1,2,……,5) is the regression coefficient;

[0020] Step 4.3, by reversely solving the quadratic polynomial regression model, an expression of L is obtained;

[0021] Step 4.4: Classify drivers according to different age groups and obtain the integer set A 1 , A 2 , A 3 , establish a mapping model of screen brightness based on different age characteristics B a (L): if Y∈A 1

[0022]

[0023] if Y∈A 2

[0024]

[0025] if Y∈A 3

[0026]

[0027] Where Y is the age of the driver; L max The maximum screen brightness;

[0028] Step 4.5: Set gender coefficient B s , combined with the screen brightness mapping model B a (L), construct the screen brightness function B(L) based on the driver's characteristics:

[0029] B(L)=B s ×B a (L) (5).

[0030] Further, in step 4.4, the A 1 For those aged 18-30, 2 31-50 years old, A 3 Aged 51-75.

[0031] Further, in step 4.5, the gender coefficient:

[0032]

[0033] Further, step 5 includes the following steps:

[0034] Step 5.1, use E(t) to represent the degree of opening and closing of the driver's eyes at time t, and the change rate of the degree of opening and closing of the driver's eyes is obtained as follows:

[0035]

[0036] Step 5.2: Compare the opening / closing degree change rate E'(t) in step 5.1 with the set adjustment threshold E' k Compare, if |E′(t)|>E′k , then the screen brightness adjustment formula is used to dynamically adjust B(L) to obtain the target screen brightness. Otherwise, the screen brightness at this time is the target screen brightness.

[0037] Furthermore, in step 5.2, the screen brightness adjustment formula is:

[0038]

[0039] Among them, B is the target screen brightness considering the driver's characteristics, D is the distance from the eye to the screen, and K 1 , K 2 They are constants used to adjust the effect of distance and eye opening on brightness. Specifically, K 1 =0.3, K 2 =0.7.

[0040] Furthermore, in step 5.2, the adjustment threshold E′ k =0.05.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention provides a method for adaptively adjusting the screen brightness of a vehicle system taking into account the characteristics of a driver. The method collects light intensity data, driver characteristics (gender, age and eye opening degree), and the screen brightness when the change in the eye opening degree of the driver before and after looking at the screen is the smallest. A mapping model for the screen brightness taking into account the characteristics of the driver is established based on the above data. The mapping model and gender are used to construct a screen brightness function based on the characteristics of the driver. The screen brightness function is adjusted in combination with the rate of change of the eye opening degree of the driver before and after looking at the screen. This method better meets the needs of different drivers for screen brightness and reduces the generation of glare and fatigue while ensuring clarity. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are incorporated in and constitute a part of this specification and, together with the description, serve to explain the principles of the present invention.

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 The present invention is a flow chart of a method for adaptively adjusting screen brightness of a vehicle system taking into account driver characteristics. DETAILED DESCRIPTION

[0046] Here, exemplary embodiments will be described in detail, and the embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples consistent with some aspects of the present invention described in detail in the appended claims.

[0047] See also Figure 1 The present invention provides a method for adaptively adjusting the screen brightness of a vehicle system taking into account the characteristics of a driver, characterized in that it comprises the following steps:

[0048] Step 1: Collecting ambient light intensity data under four different scenarios, and preprocessing the light intensity data to obtain a first data set;

[0049] Step 2: While collecting the light intensity data, collect the driver's facial image, and extract the driver's characteristics from the facial image, wherein the driver's characteristics include gender, age, and eye opening degree, to obtain a second data set;

[0050] Step 3, corresponding to four different scenarios, respectively record the screen brightness when the change in the degree of eye opening and closing of the driver's eyes is the smallest before and after he or she looks at the screen;

[0051] Step 4: establishing a mapping model of screen brightness based on the driver's age based on the first data set, the second data set and the screen brightness obtained in step 3, and combining the mapping model with gender to construct a screen brightness function based on the driver's characteristics;

[0052] Step 5: Obtain the real-time opening and closing degree of the driver's eyes, and obtain the rate of change of the eye opening and closing degree. Based on the rate of change of the eye opening and closing degree, dynamically adjust the screen brightness function in step 4 to obtain the target screen brightness that takes into account the driver's characteristics.

[0053] Furthermore, in step 1, the ambient light intensity data under four different scenarios are collected by a photosensitive sensor; the preprocessing is to clean the light intensity data to improve the accuracy and efficiency of subsequent analysis. Preferably, the algorithm that can be used for cleaning is a moving average filter. Given a light data sequence l(n) of length M, the calculation formula of the moving average filter for the i-th sampling point L(i) is as follows:

[0054]

[0055] Among them, L(i) is the smoothed light intensity value; l(n) is the original light data sequence; N represents the window length of the filter; i is the index of the current sampling point; j is the index from 0 to N-1.

[0056] Furthermore, in step 1, considering that the degree of opening and closing of the driver's eyes changes differently with light in different lighting scenarios, the lighting scenarios are divided into four types, including driving during the day (lighting conditions are always good), driving at night (lighting conditions are always poor), driving from dusk to night (lighting conditions change from good to bad), and driving from dawn to early morning (lighting conditions change from bad to good).

[0057] Furthermore, in step 2, the driver's facial image is captured by a camera, and the driver's characteristics are extracted from the driver's facial image using a deep learning method.

[0058] Specifically, in this embodiment, a convolutional neural network (CNN) architecture in a deep learning method is used to simultaneously extract features such as gender, age, and eye state (degree of eye opening) from the driver's facial image through end-to-end learning.

[0059] Further, step 4 includes the following steps:

[0060] Step 4.1, dividing the data in the first data set, the second data set and the screen brightness L into four groups of data packets according to four different scenarios, each group of the data packets including light intensity I, eye opening degree E and screen brightness L;

[0061] Step 4.2: Use a quadratic polynomial to establish a regression model for the light intensity I, eye opening degree E, and screen brightness L of each group of data packets in step 4.1. The quadratic polynomial regression model is:

[0062] E=β 0 +β 1 I+β 2 L+β 3 ·(I·L)+β 4 I 2 +β 5 ·L 2 (2);

[0063] Among them, β i (i=1,2,……,5) is the regression coefficient;

[0064] Step 4.3, by reversely solving the quadratic polynomial regression model, an expression of L is obtained;

[0065] Step 4.4: Classify drivers according to different age groups and obtain the integer set A 1 , A 2 , A 3 , a mapping model B of screen brightness based on driver age is established for different age characteristics a (L):

[0066] if Y∈A 1

[0067]

[0068] if Y∈A 2

[0069]

[0070] if Y∈A 3

[0071]

[0072] Where Y is the age of the driver; L max The maximum screen brightness;

[0073] Step 4.5: Set gender coefficient B s , combined with the screen brightness mapping model B a (L), construct the screen brightness function B(L) based on the driver's characteristics:

[0074] B(L)=B s ×B a (L) (6).

[0075] In step 4.2 and step 4.3, the light intensity I, eye opening degree E, and screen brightness L of each data packet are fitted. Specifically, the data packet corresponding to daytime driving (expressed as day) is (I day , L day 、E day ), the data packet corresponding to night driving (represented by night) is (I night , L night 、E night ), the dusk to night driving (expressed as d2n) data packet is (I d2n , L d2n 、E d2n ), the dawn to early morning driving (expressed by n2d) data packet is (I n2d , L n2d 、E n2d ).

[0076] For example, using daytime driving data (I day , L day 、E day ) to fit and get the regression model:

[0077] E day =β 0,day +β 1,day I+β 2,day L+β 3,day·(I·L)+β 4,day I 2 +β 5,day ·L 2 (7);

[0078] Use regression techniques (such as the method of least squares) to determine the coefficients in the regression model:

[0079] β i，day (i=1,2,……,5).

[0080] Similarly, we can get: E night 、E d2n 、E n2d The regression model of .

[0081] The regression model is used to reversely solve the screen brightness, taking the regression model of continuous daytime driving as an example:

[0082] E day =β 0,day +β 1,day I+β 2,day L+β 3,day ·(I·L)+β 4,day I 2 +β 5,day ·L 2 (8);

[0083] L is expressed by solving this equation:

[0084] β 5,day ·L 2 +(β 2,day +β 3,day ·I)·L+(β 0,day +β 1,day I+β 4,day I 2 -E day )=0(9);

[0085] The above equation is a standard quadratic equation and can be solved using the root-finding formula:

[0086]

[0087] Further, in step 4.4, the A 1 18-30 years old, A 2 31-50 years old, A 3 Aged 51-75.

[0088] Wherein, in step 4.5, the gender coefficient is:

[0089]

[0090] Further, step 5 includes the following steps:

[0091] Step 5.1, use E(t) to represent the degree of opening and closing of the driver's eyes at time t. From the definition of derivative, it can be concluded that the rate of change of the degree of opening and closing of the driver's eyes is:

[0092]

[0093] Step 5.2: Compare the opening / closing degree change rate E'(t) in step 5.1 with the set adjustment threshold E' k Compare and adjust the threshold E' k =0.05;

[0094] If |E′(t)|>E′ k , then the screen brightness adjustment formula is used to dynamically adjust B(L) to obtain the target screen brightness. Otherwise, the screen brightness at this time is the target screen brightness and no adjustment is required.

[0095] Among them, in step 5.2, the screen brightness adjustment formula is:

[0096]

[0097] Among them, B is the target screen brightness considering the driver's characteristics, D is the distance from the eye to the screen, and K 1 , K 2 They are constants used to adjust the effect of distance and eye opening on brightness. Specifically, K 1 =0.3, K 2 =0.7.

[0098] In formula (13), the first term represents the effect of the distance factor on the brightness; this term means that the closer the distance is, the dimmer the screen brightness is, and the greater the dynamic adjustment required. The second term represents the effect of the eye opening degree factor on the brightness; this term means that the greater the rate of change of the eye opening degree is, the greater the dynamic adjustment of the screen brightness is.

[0099] Although the present invention has been described in detail in general terms and in specific embodiments in this specification, it is obvious to those skilled in the art that some modifications or improvements may be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of protection claimed by the present invention.

Claims

1. A method for adaptively adjusting screen brightness of a vehicle system considering driver characteristics, characterized in that: The following steps are involved: Step 1: Collecting ambient light intensity data under four different scenarios, and preprocessing the light intensity data to obtain a first data set; Step 2: While collecting the light intensity data, collect the driver's facial image, and extract the driver's characteristics from the facial image, wherein the driver's characteristics include gender, age, and eye opening degree, to obtain a second data set; Step 3, corresponding to four different scenarios, respectively record the screen brightness when the change in the degree of eye opening and closing of the driver's eyes is the smallest before and after he or she looks at the screen; Step 4: establishing a mapping model of screen brightness based on the driver's age based on the first data set, the second data set and the screen brightness obtained in step 3, and combining the mapping model with gender to construct a screen brightness function based on the driver's characteristics; Step 5: Obtain the real-time opening and closing degree of the driver's eyes, and obtain the rate of change of the eye opening and closing degree. Based on the rate of change of the eye opening and closing degree, dynamically adjust the screen brightness function in step 4 to obtain the target screen brightness that takes into account the driver's characteristics.

2. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 1 is characterized in that: In step 1, ambient light intensity data under four different scenarios are collected by using a photosensitive sensor or a camera; the preprocessing is to clean the light intensity data.

3. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 1, characterized in that: In step 1, the four different scenarios include the driver driving during the day, driving at night, driving from dusk to night, and driving from dawn to early morning.

4. The method for adaptively adjusting screen brightness of a vehicle system considering driver characteristics according to claim 1, characterized in that: In step 2, the driver's facial image is collected by a camera, and the driver's characteristics are extracted from the driver's facial image using a deep learning method.

5. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 1, characterized in that: Step 4 includes the following steps: Step 4.1, dividing the data in the first data set, the second data set and the screen brightness L into four groups of data packets according to four different scenarios, each group of the data packets including light intensity I, eye opening degree E and screen brightness L; Step 4.2: Use a quadratic polynomial to establish a regression model for the light intensity I, eye opening degree E, and screen brightness L of each group of data packets in step 4.

1. The quadratic polynomial regression model is: E=β0 +β1 ·I+β2 ·L+β3 ·(I·L)+β4 ·I 2 +β5·L 2 (1); Among them, β i (i=1,2,……,5) is the regression coefficient; Step 4.3, by reversely solving the quadratic polynomial regression model, an expression of L is obtained; Step 4.4: Classify drivers according to different age groups, obtain integer sets A1, A2, A3, and establish a mapping model B of screen brightness for different age characteristics. a (L): Where Y is the age of the driver; L max The maximum screen brightness; Step 4.5: Set gender coefficient B s , combined with the screen brightness mapping model B a (L), construct the screen brightness function B(L) based on the driver's characteristics: B(L)=B s ×B a (L) (5)。 6. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 5 is characterized in that: In step 4.4, A1 is between 18 and 30 years old, A2 is between 31 and 50 years old, and A3 is between 51 and 75 years old.

7. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 5, characterized in that: In step 4.5, the gender coefficient B s for:

8. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 1, characterized in that: Step 5 includes the following steps: Step 5.1, use E(t) to represent the degree of opening and closing of the driver's eyes at time t, and the change rate of the degree of opening and closing of the driver's eyes is obtained as follows: Step 5.2: Compare the opening / closing degree change rate E'(t) in step 5.1 with the set adjustment threshold E' k Compare, if |E′(t)|>E′ k , then the screen brightness adjustment formula is used to dynamically adjust B(L) to obtain the target screen brightness. Otherwise, the screen brightness at this time is the target screen brightness.

9. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 8, characterized in that: In step 5.2, the screen brightness adjustment formula is: Among them, B is the target screen brightness considering the driver's characteristics, D represents the distance from the eyes to the screen, and K1 and K2 are constants used to adjust the effects of distance and eye opening on brightness.

10. The method for adaptively adjusting the screen brightness of a vehicle system considering the driver's characteristics according to claim 8, characterized in that: In step 5.2, the adjustment threshold E′ k =0.05.

Images