CN117746806B - Driving method, device, equipment and storage medium of mini LED backlight module - Google Patents
Driving method, device, equipment and storage medium of mini LED backlight module Download PDFInfo
- Publication number
- CN117746806B CN117746806B CN202410187803.6A CN202410187803A CN117746806B CN 117746806 B CN117746806 B CN 117746806B CN 202410187803 A CN202410187803 A CN 202410187803A CN 117746806 B CN117746806 B CN 117746806B
- Authority
- CN
- China
- Prior art keywords
- image
- backlight
- features
- image area
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000000605 extraction Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000009792 diffusion process Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000004088 simulation Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 23
- 230000009466 transformation Effects 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 14
- 230000004913 activation Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000005286 illumination Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000004313 glare Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000011430 maximum method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Landscapes
- Liquid Crystal Display Device Control (AREA)
Abstract
The invention provides a driving method, a device, equipment and a storage medium of a mini LED backlight module, wherein the method comprises the following steps: preprocessing a picture image to obtain a gray level image of the picture image; extracting the characteristics of the current ambient light data to obtain data characteristics; carrying out pixel division on the gray level image according to a plurality of dynamic dimming areas of the mini LED backlight module to obtain a plurality of image areas, and respectively carrying out feature extraction on each image area to obtain image features; inputting the image features and the data features into a backlight prediction model to obtain first backlight information; performing backlight diffusion simulation processing on the first backlight information to obtain second backlight information; and driving and controlling the mini LED backlight module based on the second backlight information. According to the method, the characteristics of each image area are extracted, and the backlight requirement of each image area can be predicted more accurately by combining the ambient light data, so that various beneficial effects of saving energy, improving display effect and the like are achieved.
Description
Technical Field
The invention relates to the field of LED dimming, in particular to a driving method, a device, equipment and a storage medium of a mini LED backlight module.
Background
MiniLED backlight control technology is an emerging display technology that uses smaller-sized LED arrays as backlights in Liquid Crystal Displays (LCDs). Compared with the traditional backlight technology, miniLED has higher brightness, higher contrast and better local dimming effect. The core of MiniLED backlight control technology is the dense arrangement of LED lattices. By integrating thousands of MiniLED light bulbs into a backlight module, finer area dimming can be achieved. This means that MiniLED can choose to turn off or reduce brightness in areas where darker backgrounds are desired, thereby providing darker black and higher contrast. In areas where brighter is desired, miniLED may increase brightness to achieve higher brightness and brighter colors. However, dimming algorithms may be simpler, resulting in poor dimming.
Disclosure of Invention
The invention mainly aims to solve the technical problem that the dimming effect of the conventional MiniLED backlight module is poor.
The first aspect of the present invention provides a driving method of a mini LED backlight module, the driving method of the mini LED backlight module includes:
Acquiring a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray level image of the picture image;
Performing region division on the mini LED backlight module according to a preset dynamic dimming region division rule to obtain a plurality of dynamic dimming regions;
acquiring current ambient light data through a preset optical sensor, and extracting features of the ambient light data to obtain data features of the ambient light data;
the gray level map is subjected to pixel division according to the dynamic dimming areas to obtain a plurality of image areas, and feature extraction is respectively carried out on each image area to obtain image features of each image area;
inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain first backlight information of each image area;
Performing backlight diffusion simulation processing on the first backlight information according to the pixel information of each pixel in each image area to obtain second backlight information of each image area;
and driving and controlling the mini LED backlight module based on the second backlight information of each image area.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray scale image of the picture image includes:
acquiring a picture image of a picture to be displayed, and extracting pixel-by-pixel information of the picture image to obtain RGB values of pixels in the picture image;
and taking the maximum value in the RGB values of each pixel as the gray value of the corresponding pixel, and generating a gray scale image of the picture image according to the gray value.
Optionally, in a second implementation manner of the first aspect of the present invention, the performing pixel division on the gray scale map according to the plurality of dynamic dimming areas to obtain a plurality of image areas, and performing feature extraction on each image area, where obtaining the image features of each image area includes:
Performing pixel division on the gray level map according to the dynamic dimming areas to obtain a plurality of image areas, and generating a corresponding pixel matrix according to RGB values of pixels in each image area;
performing convolution filtering processing on each image area according to a preset filtering function to generate a low-frequency image corresponding to each image area;
Generating a high-frequency image corresponding to the image area according to the image area and the low-frequency image;
and extracting the characteristics of the low-frequency image and the high-frequency image to obtain the image characteristics of each image area.
Optionally, in a third implementation manner of the first aspect of the present invention, the image features include a luminance feature and a texture feature; the step of extracting the features of the low-frequency image and the high-frequency image to obtain the image features of each image area comprises the following steps:
Calculating brightness information of corresponding pixels and pixel average values of corresponding image areas according to RGB values of all pixels in the low-frequency image, and generating brightness characteristics corresponding to the low-frequency image according to the brightness information of all pixels;
Calculating a first threshold value of a corresponding image area according to the pixel average value and the resolution of the display picture, and calculating a second threshold value of each image area according to a preset iterative algorithm;
And dividing image details of the high-frequency image corresponding to each image area based on the first threshold value and the second threshold value to obtain corresponding texture features.
Optionally, in a fourth implementation manner of the first aspect of the present invention, inputting the image features and the data features of each image area into a preset backlight prediction model, and obtaining the first backlight information of each image area includes:
Inputting the data features and the image features into a preset backlight prediction model, and respectively calculating attention weight vectors of the data features and the image features through an attention mechanism layer of the backlight prediction model;
The data features and the image features are weighted and fused through a feature fusion layer in the backlight prediction model according to the weight vector, so that fusion feature vectors are obtained;
And calculating first backlight information of the corresponding image area according to the fusion feature vector through a classification layer in the backlight prediction model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the calculating, by the classification layer in the backlight prediction model, the first backlight information of the corresponding image area according to the fused feature vector includes:
Mapping the fusion feature vector to a high-dimensional feature space through the classification layer in a linear transformation way to obtain a linear transformation result;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
And calculating first backlight information of the corresponding image area according to the nonlinear transformation result through a full connection layer in the classification layer.
Optionally, in a sixth implementation manner of the first aspect of the present invention, inputting the image features and the data features of each image area into a preset backlight prediction model, and obtaining the first backlight information of each image area further includes:
inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain backlight classification of each image area;
determining a backlight extraction algorithm corresponding to each image area according to the backlight classification;
And carrying out backlight extraction on the corresponding image areas according to the backlight extraction algorithm to obtain first backlight information of each image area.
The second aspect of the present invention provides a driving device for a mini LED backlight module, where the driving device for a mini LED backlight module includes:
The image processing module is used for acquiring a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray level image of the picture image;
The area dividing module is used for dividing the area of the mini LED backlight module according to a preset dynamic dimming area dividing rule to obtain a plurality of dynamic dimming areas;
the data feature extraction module is used for acquiring current ambient light data through a preset optical sensor, and extracting features of the ambient light data to obtain data features of the ambient light data;
the image feature extraction module is used for carrying out pixel division on the gray level image according to the dynamic dimming areas to obtain a plurality of image areas, and carrying out feature extraction on each image area to obtain the image features of each image area;
The backlight prediction module is used for inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain first backlight information of each image area;
the backlight diffusion module is used for carrying out backlight diffusion simulation processing on the first backlight information according to the pixel information of each pixel in each image area to obtain second backlight information of each image area;
and the driving control module is used for driving and controlling the mini LED backlight module based on the second backlight information of each image area.
The third aspect of the present invention provides a driving device for a mini LED backlight module, comprising: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line; and the at least one processor calls the instruction in the memory so that the driving equipment of the mini LED backlight module executes the steps of the driving method of the mini LED backlight module.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the steps of the method for driving a mini LED backlight module described above.
According to the driving method, the driving device, the driving equipment and the driving storage medium of the mini LED backlight module, the gray level image of the picture image is obtained by preprocessing the picture image; extracting the characteristics of the current ambient light data to obtain data characteristics; carrying out pixel division on the gray level image according to a plurality of dynamic dimming areas of the mini LED backlight module to obtain a plurality of image areas, and respectively carrying out feature extraction on each image area to obtain image features; inputting the image features and the data features into a backlight prediction model to obtain first backlight information; performing backlight diffusion simulation processing on the first backlight information to obtain second backlight information; and driving and controlling the mini LED backlight module based on the second backlight information. According to the method, the characteristics of each image area are extracted, and the backlight requirement of each image area can be predicted more accurately by combining the ambient light data, so that various beneficial effects of saving energy, improving display effect and the like are achieved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a driving method of a mini LED backlight module according to the present invention;
FIG. 2 is a schematic diagram of an embodiment of a driving apparatus of a mini LED backlight module according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an embodiment of a driving apparatus of a mini LED backlight module according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "comprising" and "having" and any variations thereof, as used in the embodiments of the present invention, are intended to cover non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.
For the convenience of understanding the present embodiment, first, a detailed description is given of a driving method of a mini LED backlight module disclosed in the present embodiment, as shown in fig. 1, and the method includes the following steps:
101. Acquiring a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray level image of the picture image;
In one embodiment of the present invention, the obtaining a frame image of a frame to be displayed and preprocessing the frame image to obtain a gray scale of the frame image includes: acquiring a picture image of a picture to be displayed, and extracting pixel-by-pixel information of the picture image to obtain RGB values of pixels in the picture image; and taking the maximum value in the RGB values of each pixel as the gray value of the corresponding pixel, and generating a gray scale image of the picture image according to the gray value.
In particular, the display may be from a variety of sources such as a digital video stream, an image file, a real-time capture device (e.g., a camera), or a graphics rendering program. This image is typically stored in digital form, each pixel containing specific color information, most commonly in RGB (red, green, blue) format, where each color channel typically has an 8-bit value representing a different color intensity. This image may undergo a series of processing procedures before being displayed. For example, it may be resized (scaled), cropped, or otherwise image processed to accommodate the specific needs of the display device. In this embodiment, the maximum method is used to generate the corresponding gray scale map, because this method can avoid making the pixel value of the image after graying too low, weaken the serious distortion caused by the excessive compensation of the pixel brightness, and LED backlights are usually more focused on brightness than color. The maximum value in RGB is selected as the gray value, which in effect selects the brightest part of the color components, which helps to better represent the luminance.
102. Performing region division on the mini LED backlight module according to a preset dynamic dimming region division rule to obtain a plurality of dynamic dimming regions;
In one embodiment of the present invention, the dynamic dimming area division rule is a set of predefined rules for determining how to divide the area on the mini LED backlight module. These rules may be based on factors such as the content of the image, brightness requirements, contrast requirements, etc. Dynamic dimming means that the brightness of the backlight area can be dynamically adjusted according to the characteristics of the image to improve the quality of the overall image. Dividing the mini LED backlight module into a plurality of areas according to a preset rule. These regions may be different brightness adjustment units allowing independent dimming of each region. Such partitioning can make the display system more flexible, adapting to different image scenes and requirements. And dividing the backlight module into a plurality of areas by applying a dividing rule, and determining corresponding dynamic dimming parameters for each area. Thus, a plurality of dynamic dimming areas are obtained, and each area can independently adjust brightness to adapt to the image characteristics of different areas. In this embodiment, the process of dynamic dimming area division includes the steps of analyzing a picture image to be displayed, knowing the characteristics of the image, such as brightness distribution, contrast, etc., and applying a preset dynamic dimming area division rule, which may include determining the size and position of an area and a brightness adjustment policy of each area. The backlight module is divided into a plurality of areas according to the rule. This involves placing mini LEDs on a backlight to form individual areas.
103. Acquiring current ambient light data through a preset optical sensor, and extracting characteristics of the ambient light data to obtain data characteristics of the ambient light data;
In one embodiment of the invention, a light sensor may be mounted in the display corresponding to the mini LED backlight module, which typically places the sensor on or around the surface of the display screen. Such a location may enable the sensor to capture the illumination of the surrounding environment. The light sensor acquires ambient light data by measuring the intensity of illumination in the surrounding environment. The sensor senses the intensity of the visible light and converts it into a digital signal representing the brightness level of the current environment. Feature extraction of ambient light data means that critical information is extracted from the raw light intensity data. This may include statistics, spectral analysis, or other methods for capturing specific features of the illumination. The result of the feature extraction is a data feature of the ambient light data, which may include the average brightness of the environment, the trend of the illumination, the spectral distribution of the illumination, etc. The acquisition and feature extraction of ambient light data may be used to dynamically adjust the brightness of the display to accommodate the current ambient lighting conditions. For example, the display may increase in brightness when ambient light is darker, and decrease in brightness in a glare environment. The purpose of such dimming is to provide a more comfortable and visual display. Changes in ambient light can directly affect the user's visual perception of the display content. In low light environments, too high a brightness may cause glare, while in high light environments, too low a brightness may cause content to be illegible. The ambient light data is acquired through the light sensor and dimming is carried out, so that user experience can be improved, and meanwhile discomfort to vision is reduced.
104. The gray level map is subjected to pixel division according to the dynamic dimming areas to obtain a plurality of image areas, and feature extraction is respectively carried out on each image area to obtain image features of each image area;
In one embodiment of the present invention, the performing pixel division on the gray scale map according to the plurality of dynamic dimming areas to obtain a plurality of image areas, and performing feature extraction on each image area, where obtaining the image features of each image area includes: performing pixel division on the gray level map according to the dynamic dimming areas to obtain a plurality of image areas, and generating a corresponding pixel matrix according to RGB values of pixels in each image area; performing convolution filtering processing on each image area according to a preset filtering function to generate a low-frequency image corresponding to each image area; generating a high-frequency image corresponding to the image area according to the image area and the low-frequency image; and extracting the characteristics of the low-frequency image and the high-frequency image to obtain the image characteristics of each image area.
Specifically, first, according to the dynamic dimming area division rule described previously, the gray scale map is divided into a plurality of areas according to a preset rule. These regions may correspond to different locations on the screen or portions of different content, each of which may be processed independently for subsequent processing. Within each dynamic dimming region, the gray scale map is pixelated. This means that pixels in the gray map are assigned to different image areas. Methods that may be used include dividing the image by a grid or by information such as the position and brightness of the pixels. For the pixels in each image area, a corresponding pixel matrix is generated according to the RGB values thereof. This matrix may represent color and brightness information within the region.
Specifically, the spatial domain image processing is mainly used in the embodiment, and is based on extraction and analysis of image texture features, and the operation processing is performed after the feature points of the image are quantized, so that the display quality of the processed final output image is better, and the power consumption of a display is lower. The spatial domain image processing refers to separating high-frequency information and low-frequency information of an image, classifying the image by extracting characteristic points of the image, and then searching for a most suitable algorithm to process various images. The high-low frequency separation is carried out on the image through the Gaussian filter, the processed image can extract the characteristics of the image, and the external noise mixed in the digitized image is eliminated, so that the visual effect of human eyes is better.
Further, the image features include a luminance feature and a texture feature; the step of extracting the features of the low-frequency image and the high-frequency image to obtain the image features of each image area comprises the following steps: calculating brightness information of corresponding pixels and pixel average values of corresponding image areas according to RGB values of all pixels in the low-frequency image, and generating brightness characteristics corresponding to the low-frequency image according to the brightness information of all pixels; calculating a first threshold value of a corresponding image area according to the pixel average value and the resolution of the display picture, and calculating a second threshold value of each image area according to a preset iterative algorithm; and dividing image details of the high-frequency image corresponding to each image area based on the first threshold value and the second threshold value to obtain corresponding texture features.
Specifically, for each pixel in the low-frequency image, the brightness information of the corresponding pixel is obtained by calculating a weighted average of RGB values or other methods. The luminance information reflects the overall luminance level of the pixel. For each image region, an average of the RGB values for all pixels within the region is calculated. This average value may be taken as representative of the overall color of the region. And generating brightness characteristics corresponding to the low-frequency image based on the calculated brightness information. This feature may include luminance distribution information throughout the image, helping to understand the overall luminance of the image.
Specifically, the first threshold value of the high-frequency image is calculated by the following formula:
；
where M and N are the resolution of the image. Wherein, For the pixel average value of each partition of the high-frequency part IHG, i and j are rows and columns after the backlight is physically divided into the regions.
For the second threshold, an initial threshold may be selected, which may be a median or other empirical value of the image gray levels. The image is divided into two regions using a selected threshold, e.g., pixels greater than the threshold are classified as one class and pixels less than or equal to the threshold are classified as another class. The pixel gray average value of the two regions is calculated. The average of the two regions is calculated and taken as a new threshold. The above steps are repeated until the change in threshold is small enough or a predetermined number of iterations is reached. In the iterative process, the threshold value gradually converges to a proper value, and the image texture detail features are divided by an upper threshold value and a lower threshold value.
105. Inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain first backlight information of each image area;
In one embodiment of the present invention, the inputting the image features and the data features of each image area into a preset backlight prediction model, and obtaining the first backlight information of each image area includes: inputting the data features and the image features into a preset backlight prediction model, and respectively calculating attention weight vectors of the data features and the image features through an attention mechanism layer of the backlight prediction model; the data features and the image features are weighted and fused through a feature fusion layer in the backlight prediction model according to the weight vector, so that fusion feature vectors are obtained; and calculating first backlight information of the corresponding image area according to the fusion feature vector through a classification layer in the backlight prediction model.
Specifically, the data features and the image features can be processed by using a neural network model fusing multiple types of features, and the neural network model fusing multiple types of features can use a multiple-input model, a depth fusion model or an attention fusion model, wherein the multiple-input model can respectively take the data features and the image features as different input layers and combine the data features and the image features into one model through a connecting layer. The deep fusion model can respectively send numerical data and image data into respective neural networks for feature extraction and classification prediction, and connect the outputs of the numerical data and the image data into a full-connection layer for comprehensive learning and classification prediction. This approach may use multiple neural network models, such as a convolutional neural network and a fully-connected neural network, to handle different types of features. While this embodiment mainly uses an attention fusion model that uses an attention mechanism to weight fuse different types of features. The method can respectively perform characteristic extraction on the digital data and the image data.
Specifically, it is assumed that an image feature vector with dimension d is obtained, and then the numerical feature and the image feature are weighted and fused using an attention mechanism at the attention mechanism layer. The importance weight of each feature can be calculated by using a self-attention mechanism (self-attention), so as to obtain attention weight vectors of the numerical feature and the image feature, then the numerical feature vector and the image feature vector are weighted and fused according to the attention weight, so as to obtain a final fusion feature vector, and finally the fusion feature vector is input into a full-connection layer for classification prediction. This layer may include multiple fully connected layers, activation functions, and loss functions for training and optimization of the model.
Further, the calculating, by the classification layer in the backlight prediction model, the first backlight information of the corresponding image area according to the fusion feature vector includes: mapping the fusion feature vector to a high-dimensional feature space through the classification layer in a linear transformation way to obtain a linear transformation result; nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained; and calculating first backlight information of the corresponding image area according to the nonlinear transformation result through a full connection layer in the classification layer.
Specifically, in this step, the model first possesses a fused feature vector, which is typically a combination of a series of features extracted from the input data (e.g., image). This feature vector is input to the classification layer where a linear transformation is performed, typically by matrix multiplication. Such a transformation can be seen as mapping the feature vector to a new space (high-dimensional feature space), which is more advantageous for the model to distinguish between different data categories or attributes. The result of the linear transformation is then processed by a predetermined activation function. The activation function is critical in neural networks, which introduces nonlinearities that enable the network to learn and model more complex relationships. Common activation functions include ReLU (linear rectification unit), sigmoid, tanh, and the like. These functions transform the input values, add complexity to the decision boundaries, and help the network capture nonlinear patterns in the input data. Finally, a full connection layer (fully connected layer) in the classification layer uses the output of the activation function. The fully connected layer is a basic component in deep learning, where each neuron is connected to all neurons of the previous layer. In this step, the full connection layer calculates backlight information of the corresponding image region according to the result of the nonlinear transformation. This means that the network generates a "first backlight information" for a given image area based on its learned features and patterns, which may involve adjustment of the brightness, contrast etc. properties of the image.
Further, inputting the image features and the data features of each image area into a preset backlight prediction model, and obtaining the first backlight information of each image area further includes: inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain backlight classification of each image area; determining a backlight extraction algorithm corresponding to each image area according to the backlight classification; and carrying out backlight extraction on the corresponding image areas according to the backlight extraction algorithm to obtain first backlight information of each image area.
Specifically, in addition to directly calculating the first backlight information through the image features and the data features, each image area may be further subjected to backlight classification through a backlight prediction model, for example, each image area is distinguished into high-brightness details, medium-brightness details, low-brightness details, medium-brightness high-details, medium-brightness low details, low-brightness high details, low-brightness medium details and low-brightness low details 9 types, and different backlight extraction algorithms are used according to different types, including maximum value method zoning dimming: backlight extraction is performed according to the maximum brightness value of each region. The method is suitable for the condition of local strong illumination. Average value zone dimming: backlight extraction is performed by calculating an average luminance value of each region. Is suitable for scenes with relatively uniform illumination. Root mean square zone dimming: the root mean square value is used as a measure of brightness for backlight extraction. Can be used in scenes sensitive to the intensity of the whole illumination. And (3) dimming by an error correction method: and comparing the error between the actual brightness and the predicted brightness to perform backlight extraction. The method is suitable for the condition of higher requirements on the brightness precision of the image. The correspondence between different backlight classifications and corresponding backlight extraction algorithms may be set in advance.
106. Performing backlight diffusion simulation processing on the first backlight information according to the pixel information of each pixel in each image area to obtain second backlight information of each image area;
In one embodiment of the invention, the first backlight information is processed by simulating the diffusion process of the backlight within the image area. This may involve modeling the physical processes of light propagation, scattering, and absorption to determine changes in the backlight within the image area. After the backlight diffusion simulation processing, second backlight information of each image area is obtained. This information reflects a more realistic and detailed distribution of the backlight in the image area, taking into account the influence of the diffusion effect on the backlight.
107. And driving and controlling the mini LED backlight module based on the second backlight information of each image area.
In one embodiment of the present invention, the backlight distribution in each image area is interpreted using the previously obtained second backlight information. This includes parameters such as brightness, color, etc. of the backlight, reflecting the fine variation of the backlight within the image area. And based on the interpreted second backlight information, an intelligent driving control strategy is formulated. This may include dynamically adjusting backlight brightness, optimizing color uniformity, and responding to specific needs of the image content. And applying the formulated driving control strategy to the mini LED backlight module. This may involve adjustments in current, brightness, off-zone control, etc. of the mini LEDs to accurately reflect the characteristics of the second backlight information. And continuously monitoring and adjusting the driving control parameters according to the change of the real-time image content. This ensures that the best display is achieved in different scenarios and responds to system feedback to improve overall performance.
In the embodiment, a gray scale of a picture image is obtained by preprocessing the picture image; extracting the characteristics of the current ambient light data to obtain data characteristics; carrying out pixel division on the gray level image according to a plurality of dynamic dimming areas of the mini LED backlight module to obtain a plurality of image areas, and respectively carrying out feature extraction on each image area to obtain image features; inputting the image features and the data features into a backlight prediction model to obtain first backlight information; performing backlight diffusion simulation processing on the first backlight information to obtain second backlight information; and driving and controlling the mini LED backlight module based on the second backlight information. According to the method, the characteristics of each image area are extracted, and the backlight requirement of each image area can be predicted more accurately by combining the ambient light data, so that various beneficial effects of saving energy, improving display effect and the like are achieved.
The driving method of the mini LED backlight module in the embodiment of the present invention is described above, and the driving device of the mini LED backlight module in the embodiment of the present invention is described below, referring to fig. 2, one embodiment of the driving device of the mini LED backlight module in the embodiment of the present invention includes:
an image processing module 201, configured to obtain a picture image of a picture to be displayed, and perform preprocessing on the picture image to obtain a gray scale of the picture image;
The area division module 202 is configured to perform area division on the mini LED backlight module according to a preset dynamic dimming area division rule, so as to obtain a plurality of dynamic dimming areas;
The data feature extraction module 203 is configured to obtain current ambient light data through a preset optical sensor, and perform feature extraction on the ambient light data to obtain data features of the ambient light data;
The image feature extraction module 204 is configured to perform pixel division on the gray scale map according to the plurality of dynamic dimming areas to obtain a plurality of image areas, and perform feature extraction on each image area to obtain image features of each image area;
The backlight prediction module 205 is configured to input the image features and the data features of each image area into a preset backlight prediction model, so as to obtain first backlight information of each image area;
the backlight diffusion module 206 is configured to perform a backlight diffusion simulation process on the first backlight information according to the pixel information of each pixel in each image area, so as to obtain second backlight information of each image area;
the driving control module 207 is configured to perform driving control on the mini LED backlight module based on the second backlight information of each image area.
In the embodiment of the invention, the driving device of the mini LED backlight module operates the driving method of the mini LED backlight module, and the driving device of the mini LED backlight module obtains a gray level image of a picture image by preprocessing the picture image; extracting the characteristics of the current ambient light data to obtain data characteristics; carrying out pixel division on the gray level image according to a plurality of dynamic dimming areas of the mini LED backlight module to obtain a plurality of image areas, and respectively carrying out feature extraction on each image area to obtain image features; inputting the image features and the data features into a backlight prediction model to obtain first backlight information; performing backlight diffusion simulation processing on the first backlight information to obtain second backlight information; and driving and controlling the mini LED backlight module based on the second backlight information. According to the method, the characteristics of each image area are extracted, and the backlight requirement of each image area can be predicted more accurately by combining the ambient light data, so that various beneficial effects of saving energy, improving display effect and the like are achieved.
The driving device of the mini LED backlight module in the embodiment of the present invention is described in detail from the perspective of the modularized functional entity in fig. 2, and the driving device of the mini LED backlight module in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 3 is a schematic structural diagram of a driving device of a mini LED backlight module according to an embodiment of the present invention, where the driving device 300 of the mini LED backlight module may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (e.g., one or more processors) and a memory 320, and one or more storage mediums 330 (e.g., one or more mass storage devices) storing applications 333 or data 332. Wherein memory 320 and storage medium 330 may be transitory or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations in the driving apparatus 300 of the mini LED backlight module. Still further, the processor 310 may be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the driving device 300 of the mini LED backlight module, so as to implement the steps of the driving method of the mini LED backlight module.
The driving apparatus 300 of the mini LED backlight module may further include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input/output interfaces 360, and/or one or more operating systems 331, such as Windows Serve, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the driving apparatus structure of the mini LED backlight module shown in fig. 3 does not constitute a limitation of the driving apparatus of the mini LED backlight module provided by the present invention, and may include more or less components than those illustrated, or may combine some components, or may have different component arrangements.
The invention also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium, and can also be a volatile computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on a computer, the instructions cause the computer to execute the steps of the driving method of the mini LED backlight module.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The driving method of the mini LED backlight module is characterized by comprising the following steps of:
Acquiring a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray level image of the picture image;
Performing region division on the mini LED backlight module according to a preset dynamic dimming region division rule to obtain a plurality of dynamic dimming regions;
acquiring current ambient light data through a preset optical sensor, and extracting features of the ambient light data to obtain data features of the ambient light data;
Performing pixel division on the gray level map according to the dynamic dimming areas to obtain a plurality of image areas, and generating a corresponding pixel matrix according to RGB values of pixels in each image area; performing convolution filtering processing on each image area according to a preset filtering function to generate a low-frequency image corresponding to each image area; generating a high-frequency image corresponding to the image area according to the image area and the low-frequency image; extracting features of the low-frequency image and the high-frequency image to obtain image features of each image area;
Inputting the data features and the image features into a preset backlight prediction model, and respectively calculating attention weight vectors of the data features and the image features through an attention mechanism layer of the backlight prediction model; the data features and the image features are weighted and fused through a feature fusion layer in the backlight prediction model according to the weight vector, so that fusion feature vectors are obtained; calculating first backlight information of the corresponding image area according to the fusion feature vector through a classification layer in the backlight prediction model;
Performing backlight diffusion simulation processing on the first backlight information according to the pixel information of each pixel in each image area to obtain second backlight information of each image area;
and driving and controlling the mini LED backlight module based on the second backlight information of each image area.
2. The driving method of the mini LED backlight module according to claim 1, wherein the obtaining a picture image of a picture to be displayed and preprocessing the picture image to obtain a gray scale of the picture image comprises:
acquiring a picture image of a picture to be displayed, and extracting pixel-by-pixel information of the picture image to obtain RGB values of pixels in the picture image;
and taking the maximum value in the RGB values of each pixel as the gray value of the corresponding pixel, and generating a gray scale image of the picture image according to the gray value.
3. The driving method of the mini LED backlight module according to claim 1, wherein the image features include brightness features and texture features; the step of extracting the features of the low-frequency image and the high-frequency image to obtain the image features of each image area comprises the following steps:
Calculating brightness information of corresponding pixels and pixel average values of corresponding image areas according to RGB values of all pixels in the low-frequency image, and generating brightness characteristics corresponding to the low-frequency image according to the brightness information of all pixels;
Calculating a first threshold value of a corresponding image area according to the pixel average value and the resolution of the display picture, and calculating a second threshold value of each image area according to a preset iterative algorithm;
And dividing image details of the high-frequency image corresponding to each image area based on the first threshold value and the second threshold value to obtain corresponding texture features.
4. The driving method of the mini LED backlight module according to claim 1, wherein the calculating, by the classification layer in the backlight prediction model, the first backlight information of the corresponding image area according to the fusion feature vector comprises:
Mapping the fusion feature vector to a high-dimensional feature space through the classification layer in a linear transformation way to obtain a linear transformation result;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
And calculating first backlight information of the corresponding image area according to the nonlinear transformation result through a full connection layer in the classification layer.
5. The method for driving a mini LED backlight module according to claim 4, wherein inputting the image features and the data features of each image area into a preset backlight prediction model, obtaining the first backlight information of each image area further comprises:
inputting the image characteristics and the data characteristics of each image area into a preset backlight prediction model to obtain backlight classification of each image area;
determining a backlight extraction algorithm corresponding to each image area according to the backlight classification;
And carrying out backlight extraction on the corresponding image areas according to the backlight extraction algorithm to obtain first backlight information of each image area.
6. The driving device of the mini LED backlight module is characterized by comprising:
The image processing module is used for acquiring a picture image of a picture to be displayed, and preprocessing the picture image to obtain a gray level image of the picture image;
The area dividing module is used for dividing the area of the mini LED backlight module according to a preset dynamic dimming area dividing rule to obtain a plurality of dynamic dimming areas;
the data feature extraction module is used for acquiring current ambient light data through a preset optical sensor, and extracting features of the ambient light data to obtain data features of the ambient light data;
The image feature extraction module is used for carrying out pixel division on the gray level image according to the dynamic dimming areas to obtain a plurality of image areas, and generating a corresponding pixel matrix according to RGB values of pixels in each image area; performing convolution filtering processing on each image area according to a preset filtering function to generate a low-frequency image corresponding to each image area; generating a high-frequency image corresponding to the image area according to the image area and the low-frequency image; extracting features of the low-frequency image and the high-frequency image to obtain image features of each image area;
The backlight prediction module is used for inputting the data features and the image features into a preset backlight prediction model, and respectively calculating attention weight vectors of the data features and the image features through an attention mechanism layer of the backlight prediction model; the data features and the image features are weighted and fused through a feature fusion layer in the backlight prediction model according to the weight vector, so that fusion feature vectors are obtained; calculating first backlight information of the corresponding image area according to the fusion feature vector through a classification layer in the backlight prediction model;
the backlight diffusion module is used for carrying out backlight diffusion simulation processing on the first backlight information according to the pixel information of each pixel in each image area to obtain second backlight information of each image area;
and the driving control module is used for driving and controlling the mini LED backlight module based on the second backlight information of each image area.
7. The driving equipment of mini LED backlight module, its characterized in that, mini LED backlight module's driving equipment includes: a memory and at least one processor, the memory having instructions stored therein;
The at least one processor invokes the instructions in the memory to cause the driving device of the mini LED backlight module to perform the steps of the driving method of the mini LED backlight module according to any one of claims 1-5.
8. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of the method for driving a mini LED backlight module according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410187803.6A CN117746806B (en) | 2024-02-20 | 2024-02-20 | Driving method, device, equipment and storage medium of mini LED backlight module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410187803.6A CN117746806B (en) | 2024-02-20 | 2024-02-20 | Driving method, device, equipment and storage medium of mini LED backlight module |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117746806A CN117746806A (en) | 2024-03-22 |
| CN117746806B true CN117746806B (en) | 2024-05-10 |
Family
ID=90251177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410187803.6A Active CN117746806B (en) | 2024-02-20 | 2024-02-20 | Driving method, device, equipment and storage medium of mini LED backlight module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117746806B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345036A (en) * | 2007-07-09 | 2009-01-14 | Nec液晶技术株式会社 | Backlight driving method of liquid crystal display device, backlight driving device, and liquid crystal display device |
| CN110473504A (en) * | 2019-08-06 | 2019-11-19 | 深圳创维－Rgb电子有限公司 | A kind of MINI LED backlight television image adjusting method and device |
| WO2021232323A1 (en) * | 2020-05-20 | 2021-11-25 | 华为技术有限公司 | Local backlight dimming method and device based on neural network |
| CN117437890A (en) * | 2023-10-30 | 2024-01-23 | 深圳新视光电科技有限公司 | Liquid crystal display energy consumption reduction method based on Mini LED backlight |
-
2024
- 2024-02-20 CN CN202410187803.6A patent/CN117746806B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345036A (en) * | 2007-07-09 | 2009-01-14 | Nec液晶技术株式会社 | Backlight driving method of liquid crystal display device, backlight driving device, and liquid crystal display device |
| CN110473504A (en) * | 2019-08-06 | 2019-11-19 | 深圳创维－Rgb电子有限公司 | A kind of MINI LED backlight television image adjusting method and device |
| WO2021232323A1 (en) * | 2020-05-20 | 2021-11-25 | 华为技术有限公司 | Local backlight dimming method and device based on neural network |
| CN117437890A (en) * | 2023-10-30 | 2024-01-23 | 深圳新视光电科技有限公司 | Liquid crystal display energy consumption reduction method based on Mini LED backlight |
Non-Patent Citations (1)
| Title |
|---|
| 基于LED背光源区域控制的高动态范围液晶显示技术进展;李福文;金伟其;邵喜斌;王霞;张丽蕾;张凯亮;;光学技术;20091115(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117746806A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109614996B (en) | Weak visible light and infrared image fusion identification method based on generation countermeasure network | |
| CN109147005B (en) | Self-adaptive dyeing method and system for infrared image, storage medium and terminal | |
| CN109979401B (en) | Driving method, driving apparatus, display device, and computer readable medium | |
| CN101360250B (en) | Immersion method and system, factor dominating method, content analysis method and parameter prediction method | |
| CN107872662A (en) | Display device | |
| CN105809643B (en) | A kind of image enchancing method based on adaptive block channel extrusion | |
| JPH06111014A (en) | Image display method and computer system | |
| CN109343692B (en) | Mobile device display power saving method based on image segmentation | |
| CN111476849B (en) | Object color recognition method, device, electronic equipment and storage medium | |
| CN108416745A (en) | A kind of image adaptive defogging Enhancement Method with color constancy | |
| CN111489322B (en) | Method and device for adding sky filter to static picture | |
| CN109948566A (en) | A kind of anti-fraud detection method of double-current face based on weight fusion and feature selecting | |
| CN111899182A (en) | Color enhancement method and device | |
| CN113095470B (en) | Training method, image processing method and device for neural network and storage medium | |
| CN113240112A (en) | Screen display adjusting method and device, electronic equipment and storage medium | |
| Li et al. | An adaptive enhancement method for low illumination color images | |
| Yu et al. | Adaptive inverse hyperbolic tangent algorithm for dynamic contrast adjustment in displaying scenes | |
| CN110009574A (en) | A kind of method that brightness, color adaptively inversely generate high dynamic range images with details low dynamic range echograms abundant | |
| CN113012188A (en) | Image fusion method and device, computer equipment and storage medium | |
| CN104240197B (en) | A kind of erasing method for keeping contrast, colour consistency and gray-scale pixels feature | |
| CN117746806B (en) | Driving method, device, equipment and storage medium of mini LED backlight module | |
| CN106803948A (en) | The effective color acquisition methods of mood light, equipment and display device | |
| Hsu et al. | A novel automatic white balance method for color constancy under different color temperatures | |
| CN109982012B (en) | Image processing method and device, storage medium and terminal | |
| CN118072664B (en) | Driving method, device, equipment and storage medium of mini LED |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |