Self-adjusting liquid crystal display based on multi-source data analysis and adjusting method thereof

Abstract

The invention relates to the field of display adjustment, in particular to a self-adjustment liquid crystal display based on multi-source data analysis and an adjustment method thereof.The method comprises the steps that an eyeball recognition model based on a YOLOv8 frame is constructed, a comprehensive loss function is constructed, and a weighted Foca loss item is determined according to the ambient light intensity and the real diameter of an eyeball; the eyeball boundary constraint item is determined based on the real eyeball diameter and the predicted eyeball diameter, the binocular constraint item is determined based on the binocular distance, and the predicted eyeball diameter and the binocular distance are determined by calculating the eyeball recognition area; determining an eyeball change area and a blinking frequency value of the user through an eyeball recognition model; and calculating an expected brightness value, and carrying out brightness self-adjustment control on the liquid crystal display based on the expected brightness value. The self-adjusting liquid crystal display based on ambient light and vision is realized, accurate brightness adjustment can be realized in combination with multi-source data such as the eyeball state of a user and the ambient light intensity, so that the user experience is improved, and the visual fatigue is reduced.

Description

Technical Field

[0001] The present invention relates to the field of display adjustment, and in particular to a self-adjusting liquid crystal display based on multi-source data analysis and an adjustment method thereof. Background Art

[0002] With the rapid development of display technology, liquid crystal displays (LCDs) have become widely used in our daily lives and work. However, prolonged use of LCDs can cause visual fatigue, especially when ambient light levels change, causing a mismatch between the display's brightness and the ambient light, which can easily cause eye discomfort. Traditional methods for adjusting display brightness typically rely on manual adjustments or simple ambient light sensor feedback mechanisms, which struggle to provide an optimal viewing experience in complex and changing lighting environments.

[0003] In recent years, attempts have been made to achieve adaptive adjustment of display brightness using ambient light sensors. However, this method is typically based on a single ambient light intensity signal and lacks comprehensive analysis of the user's eye state, making it difficult to achieve precise brightness adjustment.

[0004] Therefore, the existing display brightness adjustment method still has shortcomings in the comprehensive analysis of multi-source data and intelligent adjustment. There is an urgent need for a self-adjusting LCD display based on multi-source data analysis, which can combine multi-source data such as the user's eye state and ambient light intensity to achieve brightness adjustment that improves the visual experience and reduces visual fatigue caused by long-term use. Summary of the Invention

[0005] To this end, the present invention provides a self-adjusting liquid crystal display based on multi-source data analysis and an adjustment method thereof. By constructing a comprehensive loss function, false detections caused by strong or weak light interference are suppressed, the geometric consistency between the predicted eyeball diameter and the true value is ensured, and single-eye missed detection or offset is avoided. The eyeball positioning accuracy of the YOLOv8 model under complex lighting conditions is significantly improved, thereby realizing a self-adjusting liquid crystal display based on ambient light and vision. It can combine multi-source data such as the user's eyeball status and ambient light intensity to achieve precise brightness adjustment, thereby improving user experience and reducing visual fatigue.

[0006] To achieve the above objectives, the present invention proposes a method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis, comprising:

[0007] Obtain a user image captured by a visual sensor of a self-adjusting liquid crystal display and an ambient light intensity captured by an ambient light sensor, construct a sample test set including a correspondence between the user image and the ambient light intensity, construct an eye recognition model based on the YOLOv8 framework, construct a comprehensive loss function having a weighted Focal loss term, an eye boundary constraint term, and a binocular constraint term, and train the eye recognition model using the comprehensive loss function and the sample test set, wherein the weighted Focal loss term is determined based on the ambient light intensity and the actual eye diameter, the eye boundary constraint term is determined based on the actual eye diameter and the predicted eye diameter, the binocular constraint term is determined based on the interocular distance, and the predicted eye diameter and interocular distance are determined by calculating the eye recognition area;

[0008] Generate a user eyeball annotated image by using the eyeball recognition model for the current user image, and determine the user's eyeball change area and blink frequency value based on the eyeball annotated image;

[0009] The ambient light intensity, the eyeball change area and the blink frequency value are used to calculate an expected brightness value through a brightness conversion formula, and the brightness of the liquid crystal display is self-adjusted and controlled based on the expected brightness value.

[0010] Furthermore, the process of constructing the comprehensive loss function includes:

[0011] Constructing the weighted Focal loss term based on the product of the logarithmic function of the positive eye confidence of the sample test set, the negative eye confidence with the focus parameter as an index, and a dynamic weighting coefficient;

[0012] Calculating an exponential function of the difference between the predicted eyeball diameter and the standard eyeball diameter, and constructing the eyeball boundary constraint term based on the product of the exponential function and the eyeball dilation adjustment amount;

[0013] Constructing the binocular constraint term based on the activation function value of the predicted difference in binocular diameter and the binocular standard deviation;

[0014] The comprehensive loss function is constructed based on the weighted sum of the weighted Focal loss term, the eye boundary constraint term and the binocular constraint term.

[0015] Furthermore, the process of constructing the weighted Focal loss term includes:

[0016] Adjusting the dynamic weighting coefficient based on a comparison of the actual eyeball diameter of the sample test set used for training the eyeball recognition model with the upper limit threshold of normal eyeball diameter and the lower limit threshold of normal eyeball diameter;

[0017] The focus parameter is adjusted based on a comparison of the ambient light intensity with a bright light threshold and a dim light threshold.

[0018] Furthermore, the process of constructing the eyeball boundary constraint item includes:

[0019] Obtaining the standard eyeball diameter corresponding to the neutral light of the sample test set, and the user's historical blink frequency corresponding to the blink timing information;

[0020] Calculating the user adaptation delay duration based on the user's historical blink frequency;

[0021] The ratio of the standard eyeball diameter to the actual eyeball diameter of the sample test set is calculated, and the eyeball dilation adjustment amount is calculated with the user adaptation delay duration as an index and the ratio as a base.

[0022] Furthermore, the process of constructing the binocular constraint term includes:

[0023] The binocular constraint term is constructed by applying the difference between the predicted binocular diameter difference and the binocular standard deviation to the ReLU activation function value.

[0024] In the above scheme, the weighted focal loss term dynamically adjusts the focusing parameters according to the ambient light intensity to solve the problem of false detection caused by sudden changes in illumination. The weight is adaptively adjusted according to the actual diameter of the eyeball to improve the model's generalization ability for physiological differences. The eyeball boundary constraint term introduces an exponential function to strengthen the deviation penalty between the predicted eyeball diameter and the standard diameter to ensure the geometric consistency of pupil scaling changes. The user adaptation delay time is combined to avoid excessive adjustment. The binocular constraint term forces the two eyes to cooperate in detection to reduce the missed detection rate.

[0025] Furthermore, the process of determining the user's eyeball change area and blink frequency value based on the eyeball annotated image includes:

[0026] Determining a binary mask of the eyeball region according to the eyeball annotated image, and fitting an ellipse to the binary mask using a least squares method to calculate the eyeball diameter;

[0027] Calculate the eyeball change area by using the eyeball diameter through a sensor size conversion formula;

[0028] If the current eyeball change area is smaller than the average of the eyeball change areas for the previous set number of frames, it is determined to be a blink event;

[0029] The blink frequency value is determined based on the number of blink events of a set duration.

[0030] Furthermore, the process of calculating the expected brightness value by using the brightness conversion formula of the ambient light intensity, the eyeball change area and the blink frequency value includes:

[0031] Calculate the logarithm of the ambient light intensity plus the light intensity offset to determine a basic expected brightness value;

[0032] determining whether the eyeball is in a fatigue state based on the eyeball change area and the blink frequency value, and adjusting the zoom sensitivity if the eyeball is in a fatigue state;

[0033] Calculating an eyeball change ratio between a standard eyeball area and the eyeball change area, and calculating a brightness response gain value with the eyeball change ratio as a base and a scaling sensitivity as an exponent;

[0034] The sum of the basic expected brightness value and the brightness response gain value is used as the expected brightness value.

[0035] Furthermore, the process of performing self-adjustment control of the brightness of the liquid crystal display based on the expected brightness value includes:

[0036] Calculating a dynamic brightness factor based on the sum of a Sigmoid function value of the expected brightness value and the current brightness value and a user habit term, so as to make the dynamic brightness factor form an S-shaped transition;

[0037] The product of the dynamic brightness factor, the user-set brightness value, and the fixed factor of the current display mode is calculated to determine a display brightness value, and the brightness of the liquid crystal display is adjusted to the display brightness value.

[0038] Furthermore, the user habit item is determined based on a mean value of the user's historical brightness preference with a time decay weight.

[0039] The present invention also provides a self-adjusting liquid crystal display based on multi-source data analysis, which is provided with a visual sensor acquisition and an ambient light sensor, and is equipped with an adjustment method for the self-adjusting liquid crystal display based on multi-source data analysis.

[0040] In the above scheme, dynamic calibration of basic brightness is realized. The basic expected brightness is calculated by adding the logarithm of the ambient light intensity and the light intensity offset. This conforms to the human eye's perception characteristics of light intensity according to the Weber-Fechner law, avoids the problem of overbrightness / overdarkness caused by linear adjustment, increases sensitivity under high fatigue conditions, and rapidly improves the brightness response gain value, thus relieving visual fatigue in a timely manner.

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

[0042] 1. By constructing a comprehensive loss function to suppress false detections caused by strong or weak light interference, ensuring the geometric consistency of the predicted eye diameter with the true value, and avoiding single-eye missed detection or offset, the YOLOv8 model significantly improves the eye positioning accuracy under complex lighting conditions. This in turn enables a self-adjusting LCD display based on ambient light and vision. It can combine multiple sources of data such as the user's eye state and ambient light intensity to achieve precise brightness adjustment, thereby improving the user experience and reducing visual fatigue.

[0043] 2. The weighted focal loss term dynamically adjusts the focusing parameters based on the ambient light intensity to address false detections caused by sudden changes in illumination. The weights are adaptively adjusted based on the actual eye diameter to improve the model's generalization ability to physiological differences. The eye boundary constraint term introduces an exponential function to strengthen the penalty for deviations between the predicted eye diameter and the standard diameter, ensuring the geometric consistency of pupil scaling changes. The user adaptation delay is combined with the duration of the user adaptation to avoid over-adjustment. The binocular constraint term forces coordinated detection of both eyes to reduce the missed detection rate.

[0044] 3. Dynamic calibration of basic brightness is achieved. The basic expected brightness is calculated by adding the logarithm of the ambient light intensity and the light intensity offset. This is in line with the human eye's perception of light intensity based on the Weber-Fechner law, avoiding the overbrightness / darkness problem caused by linear adjustment. It increases sensitivity under high fatigue conditions, rapidly improves the brightness response gain value, and promptly relieves visual fatigue. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of a flow chart of a method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a comprehensive loss function construction process of an adjustment method for a self-adjusting liquid crystal display based on multi-source data analysis according to an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of a flow chart of calculating the change in eyeball area of ​​a liquid crystal display according to a method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to an embodiment of the present invention;

[0048] Figure 4 The figure is a schematic diagram of a flow chart of determining the display brightness of a liquid crystal display in a method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0051] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0052] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0053] like Figures 1 to 4 As shown, the present invention provides a self-adjusting liquid crystal display based on multi-source data analysis and an adjustment method thereof. By constructing a comprehensive loss function, false detection caused by strong light or weak light interference is suppressed, the geometric consistency between the predicted eyeball diameter and the true value is ensured, and single-eye missed detection or offset is avoided. The eyeball positioning accuracy of the YOLOv8 model under complex lighting is significantly improved, and a self-adjusting liquid crystal display based on ambient light and vision is realized. It can combine multi-source data such as the user's eyeball status and ambient light intensity to achieve precise brightness adjustment, thereby improving user experience and reducing visual fatigue.

[0054] like Figures 1 to 4 As shown, this embodiment provides a method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis, including:

[0055] Obtain a user image captured by a visual sensor of a self-adjusting liquid crystal display and an ambient light intensity captured by an ambient light sensor, construct a sample test set including a correspondence between the user image and the ambient light intensity, construct an eye recognition model based on the YOLOv8 framework, construct a comprehensive loss function having a weighted Focal loss term, an eye boundary constraint term, and a binocular constraint term, and train the eye recognition model using the comprehensive loss function and the sample test set, wherein the weighted Focal loss term is determined based on the ambient light intensity and the actual eye diameter, the eye boundary constraint term is determined based on the actual eye diameter and the predicted eye diameter, the binocular constraint term is determined based on the interocular distance, and the predicted eye diameter and interocular distance are determined by calculating the eye recognition area;

[0056] Generate a user eyeball annotated image by using the eyeball recognition model for the current user image, and determine the user's eyeball change area and blink frequency value based on the eyeball annotated image;

[0057] The ambient light intensity, the eyeball change area and the blink frequency value are used to calculate an expected brightness value through a brightness conversion formula, and the brightness of the liquid crystal display is self-adjusted and controlled based on the expected brightness value.

[0058] like Figure 2 As shown, further, the process of constructing the comprehensive loss function includes:

[0059] Constructing the weighted Focal loss term based on the product of the logarithmic function of the positive eye confidence of the sample test set, the negative eye confidence with the focus parameter as an index, and a dynamic weighting coefficient;

[0060] Calculating an exponential function of the difference between the predicted eyeball diameter and the standard eyeball diameter, and constructing the eyeball boundary constraint term based on the product of the exponential function and the eyeball dilation adjustment amount;

[0061] Constructing the binocular constraint term based on the activation function value of the predicted difference in binocular diameter and the binocular standard deviation;

[0062] The comprehensive loss function is constructed based on the weighted sum of the weighted Focal loss term, the eye boundary constraint term and the binocular constraint term.

[0063] Specifically, the comprehensive loss function is:

[0064] L total =ω d ·FL(p t ,γ dynamic )+λ1L bound (d pred )+λ2L sym (d predleft ,d predright )

[0065] Where, L total represents the comprehensive loss function, ω d ·FL(p t ,γ dynamic ) indicates that the positive confidence level p t and focusing parameter γ dynamic is the weighted Focal loss term of the variable, ω d Represents the dynamic weighting coefficient, L bound (d pred ) represents the predicted eyeball diameter d pred is the eyeball boundary constraint of the variable, L sym (d predleft ,d predright ) represents the predicted value of eye diameter d predleft ,d predrightis the binocular constraint term, and λ1 and λ2 are two weighting coefficients, preferably 0.7 and 0.3. Therefore, by constructing a comprehensive loss function that combines the weighted focal loss term, the eye boundary constraint term, and the binocular constraint term, the YOLOv8 model significantly improves eye localization accuracy under complex lighting conditions, reduces recognition errors caused by sudden changes in lighting, and significantly reduces localization errors.

[0066] Furthermore, the process of constructing the weighted Focal loss term includes:

[0067] Adjusting the dynamic weighting coefficient based on a comparison of the actual eyeball diameter of the sample test set used for training the eyeball recognition model with the upper limit threshold of normal eyeball diameter and the lower limit threshold of normal eyeball diameter;

[0068] The focus parameter is adjusted based on a comparison of the ambient light intensity with a bright light threshold and a dim light threshold.

[0069] Specifically, the weighted Focal loss term is:

[0070]

[0071] Where, ω d ·FL(p t ,γ dynamic ) represents the weighted Focal loss term, ω d represents the dynamic weighting coefficient, γ dynamic represents the focusing parameter, p t Indicates the positive confidence of the eyeball, 1-p t Indicates the negative confidence of the eyeball, α t represents the class balance weight.

[0072] Specifically, the process of adjusting the dynamic weighting coefficient is:

[0073]

[0074] Where, ω d represents the dynamic weighting coefficient, d true Represents the true eyeball diameter of the sample test set. Therefore, the dynamic weighting coefficient is increased by 50% for true eyeball diameters ≤ 7mm to compensate for the difficulty of learning small targets, and the dynamic weighting coefficient is reduced by 20% for diameters ≥ 9mm to prevent large targets from dominating the training.

[0075] Specifically, the process of adjusting the focusing parameters is:

[0076]

[0077] Where, γ dynamic represents the focusing parameter, E lightIndicates the ambient light intensity, therefore, by increasing γ under strong light dynamic Improve the focus on small pupils and reduce γ in dark environments dynamic Avoid over-suppression of easy samples.

[0078] It is understandable that the conventional Focal Loss loss function is not able to focus sufficiently on small targets of 5 to 8 mm in size. Therefore, a dynamic weighting coefficient is used to compensate for the difficulty of learning small targets, and the focusing parameters are used to improve the classification accuracy under strong light and reduce the classification accuracy in dark environments to avoid classification errors caused by excessive suppression.

[0079] Furthermore, the process of constructing the eyeball boundary constraint item includes:

[0080] Obtaining the standard eyeball diameter corresponding to the neutral light of the sample test set, and the user's historical blink frequency corresponding to the blink timing information;

[0081] Calculating the user adaptation delay duration based on the user's historical blink frequency;

[0082] Calculating a ratio of the standard eyeball diameter to the actual eyeball diameter of the sample test set, and calculating an eyeball dilation adjustment amount with the user adaptation delay duration as an index and the ratio as a base;

[0083] The eyeball boundary constraint term is constructed based on the product of the eyeball dilation adjustment amount and the exponential function.

[0084] Specifically, the eyeball boundary constraint is:

[0085]

[0086] Where, L bound (d pred ) represents the eyeball boundary constraint, d true Represents the true eyeball diameter of the sample test set, d st Represents the standard diameter of the eyeball, and obtains the standard diameter of the eyeball corresponding to the neutral light of the sample test set, for example, 9, μ represents the user adaptation delay time, is the exponential function, where d pred Represents the predicted eyeball diameter.

[0087] Specifically, the process of calculating the user adaptation delay duration based on the user's historical blink frequency is as follows:

[0088] μ=μ base +k·(HBR-BR norm )

[0089] Where μ represents the user adaptation delay time, μ baserepresents the physiological reference value, which is set to 1.5, k represents the adjustment coefficient, which is preferably an empirical value of 0.02, BR norm The HBR represents the user's historical blink rate, which is the number of blinks in the last minute. Preferably, the HBR is recalculated every 30 days to prevent habit drift.

[0090] Therefore, the eyeball boundary constraint term is used to strengthen the penalty for the predicted value exceeding the standard eyeball diameter, and the Adjust the sensitivity of the eyeball boundary constraint item to the deviation of the predicted value. When the user's historical blinking frequency is high, it indicates that eye discomfort is very likely to occur. Increasing the sensitivity will increase the recognition accuracy of the model, improve the accuracy and reliability of the prediction, and make it more consistent with the normal medical condition of the eyeball.

[0091] Furthermore, the process of constructing the binocular constraint term includes:

[0092] The binocular constraint term is constructed by applying the difference between the predicted binocular diameter difference and the binocular standard deviation to the ReLU activation function value.

[0093] Specifically, the binocular constraint item is:

[0094] L sym (d predleft ,d predright )=ReLU(|d predleft -d predright |-0.5)

[0095] Where, L sym (d predleft ,d predright ) represents the binocular constraint term, d predleft d predright Denote the predicted left and right eye diameters, respectively. 0.5 represents the binocular standard deviation, and ReLU represents the ReLU activation function. Therefore, the binocular constraint penalizes predicted values ​​that exceed the normal binocular standard deviation by 0.5 mm, ensuring that the prediction results are consistent with normal binocular conditions.

[0096] Specifically, the eye recognition model training process uses data collected from the official repository git and the LCD display's visual sensor and ambient light sensor to jointly construct the YOLO standard training and test set that annotates the eye area. The pre-trained weighted yolov8n model is loaded, and the training parameters are set: training round epochs = 100, input resolution imgsz = 640, batch size batch = 16, GPU ID uses dual-card device = [0, 1], data loading thread number workers = 2, automatic data augmentation (Mosaic / MixUp) augment = True, confidence threshold conf = 0.25, and IoU threshold iou = 0.6. The yolov8n model also uses a built-in cosine annealing strategy that does not require manual settings. The yolov8n model is trained and tested based on the comprehensive loss function until the value of the comprehensive loss function meets the confidence threshold and the IoU meets the IoU threshold, thereby generating the eye recognition model.

[0097] In the above scheme, the weighted focal loss term dynamically adjusts the focusing parameters according to the ambient light intensity to solve the problem of false detection caused by sudden changes in illumination. The weight is adaptively adjusted according to the actual diameter of the eyeball to improve the model's generalization ability for physiological differences. The eyeball boundary constraint term introduces an exponential function to strengthen the deviation penalty between the predicted eyeball diameter and the standard diameter to ensure the geometric consistency of pupil scaling changes. The user adaptation delay time is combined to avoid excessive adjustment. The binocular constraint term forces the two eyes to cooperate in detection to reduce the missed detection rate.

[0098] like Figure 3 As shown, further, the process of determining the user's eyeball change area and blink frequency value based on the eyeball annotated image includes:

[0099] Determining a binary mask of the eyeball region according to the eyeball annotated image, and fitting an ellipse to the binary mask using a least squares method to calculate the eyeball diameter;

[0100] Calculate the eyeball change area by using the eyeball diameter through a sensor size conversion formula;

[0101] If the current eyeball change area is smaller than the average of the eyeball change areas for the previous set number of frames, it is determined to be a blink event;

[0102] The blink frequency value is determined based on the number of blink events of a set duration.

[0103] Specifically, the process of calculating the eyeball diameter is:

[0104]

[0105] Where x c ,y crepresents the coordinates of the center of the ellipse, a and b represent the eyeball diameter, including the major radius and minor axis radius of the ellipse, θ represents the rotation angle of the ellipse, and x and y represent the coordinates of the eyeball area belonging to the binary mask M. Therefore, the above formula can calculate a and b as the eyeball diameter.

[0106] Specifically, the sensor size conversion formula is:

[0107]

[0108] Where A t Indicates the change in eyeball area, d pixel It represents the average diameter of the eyeball, which is the average of the major radius a and the minor radius b of the ellipse. sensor Indicates the size of the visual sensor, for example, a camera sensor is 50mm 2 , f represents the focal length of the visual sensor (in mm), r image Indicates the image resolution.

[0109] It can be understood that the above-mentioned process of determining the average eyeball diameter is also used to label the actual eyeball diameter of the sample test set and the predicted eyeball diameter output by the model.

[0110] Specifically, if the eyeball change area is smaller than the average of the eyeball change areas in the previous 30 frames, it is determined to be a blink event.

[0111] like Figure 4 As shown, further, the process of calculating the expected brightness value by using the brightness conversion formula of the ambient light intensity, the eyeball change area and the blink frequency value includes:

[0112] Calculate the logarithm of the ambient light intensity plus the light intensity offset to determine a basic expected brightness value;

[0113] determining whether the eyeball is in a fatigue state based on the eyeball change area and the blink frequency value, and adjusting the zoom sensitivity if the eyeball is in a fatigue state;

[0114] Calculating an eyeball change ratio between a standard eyeball area and the eyeball change area, and calculating a brightness response gain value with the eyeball change ratio as a base and a scaling sensitivity as an exponent;

[0115] The sum of the basic expected brightness value and the brightness response gain value is used as the expected brightness value.

[0116] Specifically, the expected brightness value is:

[0117]

[0118] Where B exp represents the expected brightness value, α·ln(Eenv +β) represents the basic expected brightness value, α is the dynamic coefficient, which is adjusted according to user habits, E env Indicates the ambient light intensity, β indicates the light intensity offset, preferably the basic light compensation value is 10lux, Represents the brightness response gain value, where A st Indicates the standard area of ​​the eyeball, A t Represents the area of ​​eyeball change, γ represents the eyeball response gain, preferably 0.1-0.3, which suppresses brightness oscillations caused by overcompensation, and δ represents the scaling sensitivity. It can be understood that the eyeball response gain γ (0.1-0.3) can suppress brightness oscillations caused by overcompensation, and the scaling sensitivity δ is used to match the expected brightness value with the Weber-Fechner law of human eye brightness perception. The Weber-Fechner law states that the brightness intensity perceived by the human eye is proportional to the logarithm of the stimulus intensity, and the basic expected brightness value (indicating that the human eye's perception of brightness is based on a certain ambient light background) reflects this logarithmic relationship, that is, the setting of the basic expected brightness value is based on the logarithmic response characteristics of the human eye to ambient light intensity. And the brightness response gain value It reflects the nonlinear (logarithmic-related) response mechanism of the human eye to the relative change in brightness when perceiving changes in the Weber-Fechner law, and through the eye response gain γ and scaling sensitivity δ, the expected brightness value calculated by the entire formula is made to conform to the nonlinear, relatively sensitive and logarithmic-like characteristics of the human eye's actual perception of brightness.

[0119] Specifically, the fatigue state is triggered when the eyeball change area and the blink frequency value exceed the reference value by 30% for 5 seconds. The specific calculation process of the scaling sensitivity δ is:

[0120]

[0121] like Figure 4 As shown, further, the process of performing self-adjustment control of the brightness of the liquid crystal display based on the expected brightness value includes:

[0122] Calculating a dynamic brightness factor based on the sum of a Sigmoid function value of the expected brightness value and the current brightness value and a user habit term, so as to make the dynamic brightness factor form an S-shaped transition;

[0123] The product of the dynamic brightness factor, the user-set brightness value, and the fixed factor of the current display mode is calculated to determine a display brightness value, and the brightness of the liquid crystal display is adjusted to the display brightness value.

[0124] Specifically, the Sigmoid function value is:

[0125]

[0126] Where B(t) represents the Sigmoid function value, that is, the ambient light intensity adjustment value at time t, and B start Indicates the current display brightness, B exp represents the desired brightness value, t0 represents the center switching time point of the S-shaped transition, t represents the current time, and k represents the steepness of the curve, preferably 0.8. Therefore, using the S-shaped curve (Sigmoid) gradient can eliminate the step effect of linear adjustment.

[0127] Specifically, the calculation process of the dynamic brightness factor is DBF = B(t) + h(U p ,U h ), where DBF represents the dynamic brightness factor, B(t) represents the Sigmoid function value, h(U p ,U h ) indicates user habit items.

[0128] Specifically, the calculation process of the display brightness value is: actua =B set ×F fixed ×DBF, where B actua Indicates the display brightness value, B set Indicates the brightness value set by the user, F fixed Indicates the fixed factor of the current display mode, such as eye protection mode F fixed It is 0.8, DBF stands for dynamic brightness factor.

[0129] Furthermore, the user habit item is determined based on a mean value of the user's historical brightness preference with a time decay weight.

[0130] Specifically, the calculation process of the user habit item is:

[0131]

[0132] Where, h(U p ,U h ) represents the user habit item, U p Indicates the current screen brightness value, U h represents the user's historical brightness preference value, σ represents the Sigmoid activation function, and w i is the time decay weight at time point i, Used to obtain the average historical brightness preference of users based on time decay weights for period n, U i is the user's historical brightness preference value at time point i, where the time decay weight t now Indicates the current time point, t i Represents the historical time point i, so that the farther the historical time point is from the current time point, the smaller the time decay weight.

[0133] Furthermore, the tool MonitorControl is used to adjust the display brightness to the display brightness value through the DDC / CI protocol.

[0134] This embodiment also provides a self-adjusting liquid crystal display based on multi-source data analysis, which is equipped with a visual sensor acquisition and an ambient light sensor, and is equipped with an adjustment method for the self-adjusting liquid crystal display based on multi-source data analysis.

[0135] In the above scheme, dynamic calibration of basic brightness is realized. The basic expected brightness is calculated by adding the logarithm of the ambient light intensity and the light intensity offset. This conforms to the human eye's perception characteristics of light intensity according to the Weber-Fechner law, avoids the problem of overbrightness / overdarkness caused by linear adjustment, increases sensitivity under high fatigue conditions, and rapidly improves the brightness response gain value, thus relieving visual fatigue in a timely manner.

[0136] In this embodiment, a comprehensive loss function is constructed to suppress false detections caused by strong or weak light interference, ensure the geometric consistency of the predicted eyeball diameter with the true value, avoid single-eye missed detection or offset, and significantly improve the eye positioning accuracy of the YOLOv8 model under complex lighting conditions. This in turn realizes a self-adjusting LCD display based on ambient light and vision. It can combine multiple sources of data such as the user's eye state and ambient light intensity to achieve precise brightness adjustment, thereby improving the user experience and reducing visual fatigue. The weighted Focal loss term dynamically adjusts the focus parameters based on the ambient light intensity to address the problem of false detection caused by sudden changes in illumination. The weights are adaptively adjusted according to the true eyeball diameter, improving the model's generalization ability to physiological differences. The eyeball boundary constraint term introduces an exponential function to strengthen the penalty for deviations between the predicted eyeball diameter and the standard diameter, ensuring geometric consistency of pupil zoom changes. It combines the user's adaptation delay to avoid over-adjustment. The binocular constraint term forces the two eyes to conduct coordinated detection, reducing the missed detection rate. Dynamic calibration of basic brightness is achieved. The basic expected brightness is calculated by adding the logarithm of the ambient light intensity and the light intensity offset. This conforms to the human eye's perception of light intensity based on the Weber-Fechner law, avoids the overbrightness / overdarkness problem caused by linear adjustment, increases sensitivity under high fatigue conditions, rapidly improves the brightness response gain value, and promptly relieves visual fatigue.

[0137] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0138] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis, characterized in that: include: Obtain a user image captured by a visual sensor of a self-adjusting liquid crystal display and an ambient light intensity captured by an ambient light sensor, construct a sample test set including a correspondence between the user image and the ambient light intensity, construct an eye recognition model based on the YOLOv8 framework, construct a comprehensive loss function having a weighted Focal loss term, an eye boundary constraint term, and a binocular constraint term, and train the eye recognition model using the comprehensive loss function and the sample test set, wherein the weighted Focal loss term is determined based on the ambient light intensity and the actual eye diameter, the eye boundary constraint term is determined based on the actual eye diameter and the predicted eye diameter, the binocular constraint term is determined based on the interocular distance, and the predicted eye diameter and interocular distance are determined by calculating the eye recognition area; Generate a user eyeball annotated image by using the eyeball recognition model for the current user image, and determine the user's eyeball change area and blink frequency value based on the eyeball annotated image; The ambient light intensity, the eyeball change area and the blink frequency value are used to calculate an expected brightness value through a brightness conversion formula, and the brightness of the liquid crystal display is self-adjusted and controlled based on the expected brightness value.

2. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 1, characterized in that: The process of constructing the comprehensive loss function includes: Constructing the weighted Focal loss term based on the product of the logarithmic function of the positive eye confidence of the sample test set, the negative eye confidence with the focus parameter as an index, and a dynamic weighting coefficient; Calculating an exponential function of the difference between the predicted eyeball diameter and the standard eyeball diameter, and constructing the eyeball boundary constraint term based on the product of the exponential function and the eyeball dilation adjustment amount; Constructing the binocular constraint term based on the activation function value of the predicted difference in binocular diameter and the binocular standard deviation; The comprehensive loss function is constructed based on the weighted sum of the weighted Focal loss term, the eye boundary constraint term and the binocular constraint term.

3. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 2, characterized in that: The process of constructing the weighted Focal loss term includes: Adjusting the dynamic weighting coefficient based on a comparison of the actual eyeball diameter of the sample test set used for training the eyeball recognition model with the upper limit threshold of normal eyeball diameter and the lower limit threshold of normal eyeball diameter; The focus parameter is adjusted based on a comparison of the ambient light intensity with a bright light threshold and a dim light threshold.

4. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 2, characterized in that: The process of constructing the eyeball boundary constraint item includes: Obtaining the standard eyeball diameter corresponding to the neutral light of the sample test set, and the user's historical blink frequency corresponding to the blink timing information; Calculating the user adaptation delay duration based on the user's historical blink frequency; The ratio of the standard eyeball diameter to the actual eyeball diameter of the sample test set is calculated, and the eyeball dilation adjustment amount is calculated with the user adaptation delay duration as an index and the ratio as a base.

5. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 2, characterized in that: The process of constructing the binocular constraint term includes: The binocular constraint term is constructed by applying the difference between the predicted binocular diameter difference and the binocular standard deviation to the ReLU activation function value.

6. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 1, characterized in that: The process of determining the user's eyeball change area and blink frequency value according to the eyeball annotated image includes: Determining a binary mask of the eyeball region according to the eyeball annotated image, fitting an ellipse to the binary mask using a least squares method, and calculating the eyeball diameter; Calculate the eyeball change area by using the eyeball diameter through a sensor size conversion formula; If the current eyeball change area is smaller than the average of the eyeball change areas for the previous set number of frames, it is determined to be a blink event; The blink frequency value is determined based on the number of blink events of a set duration.

7. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 1, characterized in that: The process of calculating the expected brightness value by using the brightness conversion formula of the ambient light intensity, the eyeball change area and the blink frequency value includes: Calculate the logarithm of the ambient light intensity plus the light intensity offset to determine a basic expected brightness value; determining whether the eyeball is in a fatigue state based on the eyeball change area and the blink frequency value, and adjusting the zoom sensitivity if the eyeball is in a fatigue state; Calculating an eyeball change ratio between a standard eyeball area and the eyeball change area, and calculating a brightness response gain value with the eyeball change ratio as a base and a scaling sensitivity as an exponent; The sum of the basic expected brightness value and the brightness response gain value is used as the expected brightness value.

8. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to any one of claims 1 to 7, characterized in that: The process of performing self-adjustment control of brightness of the liquid crystal display based on the expected brightness value includes: Calculating a dynamic brightness factor based on the sum of a Sigmoid function value of the expected brightness value and the current brightness value and a user habit term, so as to make the dynamic brightness factor form an S-shaped transition; The product of the dynamic brightness factor, the user-set brightness value, and the fixed factor of the current display mode is calculated to determine a display brightness value, and the brightness of the liquid crystal display is adjusted to the display brightness value.

9. The method for adjusting a self-adjusting liquid crystal display based on multi-source data analysis according to claim 8, characterized in that: The user habit item is determined based on the average of the user's historical brightness preferences with a time decay weight.

10. A self-adjusting liquid crystal display based on multi-source data analysis, characterized in that: The device is provided with a visual sensor collection and an ambient light sensor, and is equipped with an adjustment method for a self-adjusting liquid crystal display based on multi-source data analysis as claimed in any one of claims 1 to 9.

Images