OLED display screen frame rate intelligent control system and method based on image analysis

Abstract

This invention discloses an intelligent frame rate control system and method for OLED displays based on image analysis, relating to the field of display frame rate control. The invention acquires the overall state and clarity of the image of the display screen to be adjusted at equal intervals. When the clarity of the image of the display screen to be adjusted does not meet the requirements, the playback frame rate of the display screen is adjusted to change the corresponding image clarity, thereby ensuring that the image clarity of the display screen at that point in time meets the requirements. Furthermore, after the local clarity of the video meets the requirements, the acquisition interval of the display screen image is adjusted from the perspective of the overall clarity of the played video, so that the overall clarity of the played video reaches its optimal level, resulting in a better viewing experience. By adjusting the acquisition interval, the probability of the video image clarity not meeting the requirements within the acquisition interval is reduced, thus improving the overall clarity of the video.

Description

Technical Field

[0001] This invention belongs to the field of display screen frame rate control, and more specifically, it relates to an intelligent frame rate control system and method for OLED displays based on image analysis. Background Technology

[0002] Chinese Patent No. CN112102780B discloses a display frame rate control method, device, and computer-readable storage medium, including monitoring the current foreground program, determining the application type of the foreground program, and identifying the current functional interface of the foreground program; then determining the main content area of ​​the functional interface and identifying the display content within the main content area; determining the current display frame rate based on the application type and the content characteristics of the display content; and finally, adjusting the operating parameters of the terminal device's display screen according to the display frame rate during the display period of the display content.

[0003] When playing videos on an OLED display, if the frame rate does not meet the requirements for the dynamic range and complexity of the scene, noticeable stuttering will occur, especially in scenes with rapid changes or fast-moving objects. This stuttering will be more severe, affecting the viewing experience. It may also cause the actions in the scene to appear disjointed, such as the body movements of people or the trajectory of objects, making them look stiff and unnatural, failing to present a smooth dynamic effect. In cases with high scene complexity, insufficient frame rate may lead to problems such as blurring and distortion. Summary of the Invention

[0004] To address the problems in related technologies, this invention proposes an intelligent frame rate control system and method for OLED displays based on image analysis, in order to overcome the aforementioned technical problems existing in the prior art.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] This invention relates to an intelligent frame rate control method for OLED displays based on image analysis, comprising the following steps:

[0007] S1. Set several state quantity levels corresponding to several display screen state quantity types and combine them to obtain a comprehensive display screen state set.

[0008] S2. Collect multiple historical images and corresponding comprehensive status data of the display screen when playing video based on the comprehensive status set of the display screen. Then collect the clarity data, comprehensive status data and corresponding playback frame data of the multiple historical images and construct the comprehensive status mapping model and the clarity mapping model of the display screen.

[0009] S3. In conjunction with the display screen image comprehensive status mapping model and the display screen image clarity mapping model, the display screen image of the display screen to be adjusted is collected by setting the current image data collection interval and the corresponding current display screen image comprehensive status data is mapped out. Then the corresponding current display screen image clarity data is mapped out. Finally, the frame rate of the video played on the display screen to be adjusted is adjusted to obtain the adjusted current display screen video.

[0010] S4. Adjust the current screen image data acquisition interval according to the adjusted current display video;

[0011] This solution sets several comprehensive states for the OLED display screen's image and combines them with a constructed comprehensive state mapping model and a resolution mapping model to acquire the comprehensive state and resolution of the image of the display screen to be adjusted at equal intervals. When the resolution of the image of the display screen to be adjusted does not meet the requirements, the playback frame rate of the display screen to be adjusted is adjusted to change the corresponding resolution, thereby ensuring that the resolution of the image of the display screen at that point in time meets the requirements. Since the image of the display screen is acquired at intervals, if the interval time is unreasonable, the already adjusted frame rate may again fail to meet the frame rate requirements of the playback scene during the interval time. Based on this, this solution adjusts the acquisition interval time of the display screen image from the perspective of the overall resolution of the played video, so that the overall resolution of the played video reaches the optimal level, thereby providing a better viewing experience.

[0012] Preferably, step S1 includes the following steps:

[0013] S11. Define several state variable types related to the frame rate of the OLED display, and obtain the display state variable type set a1 = {a 11 ,a 12}, a 11 a 12 These represent the dynamic level state quantity type and the complexity state quantity type of the screen, respectively. Based on the screen state quantity type set, several state quantity levels and corresponding state quantity value ranges are set for each screen state quantity type, resulting in a dynamic level level set, a dynamic level range set, a complexity level set, and a complexity range set.

[0014] S12. Combine the set of image dynamic level levels and the set of image complexity levels to obtain several comprehensive states of the OLED display screen, resulting in a set of comprehensive display screen states and a corresponding set of image dynamic complexity combinations a2; as follows.

[0015]

[0016] in, ...

[0017] This solution sets the overall state of the display screen from two perspectives: the dynamic range of the image and the complexity of the image. Both of these aspects are closely related to the frame rate of the video played on the display screen. The greater the dynamic range of the image, the higher the frame rate is required to ensure its clarity, and the greater the complexity of the image, the higher the frame rate is required to ensure its clarity.

[0018] Preferably, step S2 includes the following steps:

[0019] S21. Set the OLED display screen that needs to be adjusted in terms of frame rate, and denot it as the display screen to be adjusted in terms of frame rate; in conjunction with the display screen overall state set, the dynamic complexity combination set, the dynamic level set, the dynamic range set, the complexity level set, and the complexity range set, collect multiple historical screen images and corresponding display screen overall state data when the display screen to be adjusted plays video, and obtain the historical display screen image dataset and the first historical display screen overall state dataset.

[0020] In addition, the clarity data, overall image status data, and frame number data of the corresponding historical images of the display screen to be adjusted are collected, as well as the frame number data of the corresponding display screen playing video, to obtain the historical image clarity dataset, the second historical display screen overall image status dataset, and the historical video playback frame number dataset.

[0021] S22. Construct a comprehensive state mapping model for the display screen using the historical display screen image dataset and the first historical display screen comprehensive state dataset.

[0022] S23. Construct a display screen clarity mapping model based on the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset.

[0023] By collecting historical display screen image datasets and a first historical display screen comprehensive status dataset, data support was provided for the subsequent construction of a display screen comprehensive status mapping model; by collecting historical image clarity datasets, a second historical display screen comprehensive status dataset, and historical video playback frame count datasets, data support was provided for the subsequent construction of a display screen clarity mapping model.

[0024] The display screen overall status mapping model provides a mapping tool for subsequent real-time acquisition of the overall status of the display screen, thereby facilitating the acquisition of corresponding screen clarity data through the display screen clarity mapping model.

[0025] Preferably, step S3 includes the following steps:

[0026] S31. Set the time interval for collecting the image data of the display screen to be adjusted, and record it as the current image data collection interval; when the display screen to be adjusted is playing video, collect the image of the display screen to be adjusted according to the current image data collection interval, and use the image of the display screen to be adjusted at the current moment as the current image data of the display screen to be adjusted.

[0027] S32. Obtain the frame count data when the video is played on the display screen to be adjusted in S31, and obtain the current video playback frame count data of the display screen; input the current display screen image data to be adjusted into the display screen image comprehensive state mapping model for mapping, and obtain the current display screen image comprehensive state data of the display screen to be adjusted.

[0028] Set a first threshold for the image clarity of the display screen to be adjusted; input the current comprehensive status data of the display screen to be adjusted and the current video playback frame rate data of the display screen into the display screen image clarity mapping model for mapping to obtain the current image clarity data of the display screen to be adjusted;

[0029] S33. When the current display screen resolution data to be adjusted is less than the first display screen resolution threshold, the current display screen video playback frame rate data is adjusted to obtain the current final display screen video playback frame rate data; otherwise, it is not necessary to adjust the current display screen video playback frame rate data.

[0030] The current final display screen video playback frame rate data is used as the frame rate of the video playing on the display screen to be adjusted at the current moment;

[0031] S34. Take the image data after the next time interval of the current display screen image data to be adjusted as the current display screen image data to be adjusted, and repeat S31, S32, S33 and S34; when the current display screen image data to be adjusted is the image data after the last time interval, stop repeating; and obtain the adjusted current display screen video.

[0032] Because the image on an OLED display is constantly changing during video playback, image data is acquired at equal intervals for analysis. When the clarity does not meet requirements, the frame rate of the video can be adjusted in a timely manner. This ensures that when playing a particular segment, the frame rate of the entire video is adjusted to a level suitable for that segment's playback requirements. Since a higher frame rate means more power consumption, the goal is to minimize the power consumption of the entire video playback while ensuring that the clarity of the segment meets the requirements.

[0033] Preferably, step S4 includes the following steps:

[0034] S41. Set the image clarity threshold of the second display screen to be adjusted; measure the overall clarity of the adjusted current display screen video to obtain the overall clarity data of the current display screen video;

[0035] S42. When the overall clarity data of the current display screen video is less than the second display screen clarity threshold to be adjusted, the current image data acquisition interval is adjusted until the overall clarity data of the current display screen video is greater than or equal to the second display screen clarity threshold to be adjusted; otherwise, it is not necessary to adjust the current image data acquisition interval.

[0036] By setting a resolution threshold for the second display screen to be adjusted, a quantitative basis is provided for determining whether the overall resolution of the video meets the requirements after the resolution of each part of the video is adjusted. Since the scene of the video may suddenly change within the interval, such as the sudden appearance of a highly dynamic or complex scene, the frame rate of the video is still set according to the previous lower dynamic or lower complexity scene. Therefore, the resolution of the video playback within the interval is lower, which affects the overall resolution of the video. Therefore, by adjusting the acquisition interval, the probability of sudden changes in video content is reduced, thereby reducing the probability of the video resolution not meeting the requirements within the acquisition interval and improving the overall resolution of the video.

[0037] Preferably, adjusting the current image data acquisition interval in S42 includes the following steps:

[0038] S421. Set the value range of the current image data acquisition interval to obtain the current acquisition interval value range. These represent the lower limit and upper limit of the current frame image data acquisition interval, respectively;

[0039] The image acquisition interval is used to adjust the squirrel population; the maximum number of iterations for adjusting the squirrel population based on the image acquisition interval is set to [value missing]. And the current iteration number is These are respectively denoted as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment; the search space dimension of the squirrel population for the image acquisition interval adjustment is 1;

[0040] S422. Based on the current acquisition interval range, adjust the initial position of each squirrel in the squirrel population by setting the image acquisition interval and obtaining the second initial position set. b 2i b'2 indicates that the image acquisition interval adjusts the initial position of the i-th squirrel in the squirrel population, and b'2 indicates that the image acquisition interval adjusts the size of the squirrel population; b 2i The calculation formula is as follows:

[0041]

[0042] In the formula, rand 2i Indicates that b 2i Generate random numbers between 0 and 1;

[0043] S423. Construct the fitness function b′2 for adjusting the image acquisition interval of the squirrel population; as follows.

[0044]

[0045] In the formula, This means replacing the current image data acquisition interval with the image acquisition interval data obtained from each iteration, and executing the adjusted overall clarity data of the current display screen video obtained from S31, S32, S33, and S34.

[0046] S424. Begin iteration. Before iteration, set the current iteration count of the interval adjustment to 1. During the first iteration, use the fitness function b′2 of the squirrel population to calculate the fitness value of the initial position of each squirrel in the second initial position set, and obtain the third fitness value set. Take the largest fitness value in the third fitness value set and the corresponding initial position of the squirrel as the third global best fitness and the third global best position, respectively. Update the initial position of each squirrel in the second initial position set according to the third global best fitness and the third global best position. After the update is completed, increment the current iteration count of the interval adjustment by 1 and enter the next iteration.

[0047] In each iteration, the fitness function b′2 of the squirrel population for adjusting the image acquisition interval is used to calculate the fitness value of the position of each squirrel in the squirrel population for adjusting the image acquisition interval obtained in the previous iteration, resulting in a fourth fitness value set. The maximum fitness value in the fourth fitness value set and the position of the corresponding squirrel are taken as the fourth global best fitness and the fourth global best position, respectively. The position of each squirrel in the squirrel population for adjusting the image acquisition interval obtained in the previous iteration is updated according to the fourth global best fitness and the fourth global best position. After the update is completed, the current iteration number of the interval adjustment is incremented by 1 and the next iteration is started.

[0048] S425. When a~4≥a~3, stop the iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue the iteration until a~4≥a~3; use the second final global optimal fitness as the optimized overall video clarity data of the current display screen; when the optimized overall video clarity data of the current display screen is greater than or equal to the second screen clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 to continue the iteration until the optimized overall video clarity data of the current display screen is greater than or equal to the second screen clarity threshold to be adjusted.

[0049] The Squirrel Optimization Algorithm (SSEO) can perform not only global searches but also fine-grained searches within local regions, thus improving its optimization capabilities. It is insensitive to the choice of initial values; different initial values ​​may lead the algorithm down different paths during the search process, but all will eventually converge to a better solution. During the search process, it effectively handles the influence of noise and outliers, thereby improving the algorithm's robustness. It can be applied to various optimization problems, including function optimization, combinatorial optimization, and parameter optimization in machine learning, exhibiting strong versatility and scalability. Based on these advantages, this scheme uses the Squirrel Optimization Algorithm to iteratively adjust the current image data acquisition interval, using the overall clarity of the played video as the fitness function. Therefore, as the iteration progresses, the overall clarity of the played video increases, eventually meeting the requirements.

[0050] The image analysis-based intelligent frame rate control system for OLED displays includes an OLED display status level setting module, a comprehensive image status setting module, a historical display data acquisition module, a mapping model construction module, a frame rate adjustment module for the display to be adjusted, and an image acquisition interval adjustment module.

[0051] The OLED display state quantity level setting module is used to set several state quantity levels corresponding to several display state quantity types to obtain a set of dynamic level levels and a set of complex level levels.

[0052] The overall screen status setting module is used to combine the screen dynamic level set and the screen complexity level set to obtain the overall screen status set of the display screen.

[0053] The historical display screen data acquisition module is used to acquire multiple historical screen images, corresponding display screen overall status data, clarity data of multiple historical screen images, overall status data, and corresponding frame number data of the display screen playing video, based on the display screen overall status set, screen dynamic level set, and screen complexity level set, to obtain a historical display screen image dataset, a first historical display screen overall status dataset, a historical screen clarity dataset, a second historical display screen overall status dataset, and a historical video playback frame number dataset.

[0054] The mapping model construction module is used to construct a display screen image comprehensive status mapping model and a display screen image clarity mapping model based on the historical display screen image dataset, the first historical display screen image comprehensive status dataset, the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset.

[0055] The frame rate adjustment module for the display screen to be adjusted is used in conjunction with the display screen image comprehensive state mapping model and the display screen image clarity mapping model. By setting the current image data acquisition interval, it acquires the image of the display screen to be adjusted and maps the corresponding current display screen image comprehensive state data. Then, it maps the corresponding current display screen image clarity data based on the current display screen image comprehensive state data. Finally, it adjusts the frame rate of the video played on the display screen to be adjusted based on the current display screen image clarity data to obtain the adjusted current display screen video.

[0056] The image acquisition interval adjustment module is used to adjust the current image data acquisition interval based on the adjusted current display screen video.

[0057] The present invention has the following beneficial effects:

[0058] 1. In this invention, the overall state and clarity of the image of the display screen to be adjusted are acquired at equal intervals. When the clarity of the image of the display screen to be adjusted does not meet the requirements, the playback frame rate of the display screen to be adjusted is adjusted to change the corresponding image clarity, thereby making the image clarity of the display screen at that time point meet the requirements. After the local clarity of the video meets the requirements, the acquisition interval of the display screen image is adjusted from the perspective of the overall clarity of the video playback, so that the overall clarity of the video playback reaches the optimal level, thereby making the playback have a better viewing experience.

[0059] 2. In this invention, since a higher frame rate in video playback means more power consumption, the local video frame is individually adjusted to minimize the power consumption of the entire video playback, while ensuring that the clarity of the segment meets the requirements.

[0060] 3. By adjusting the acquisition interval, this invention reduces the probability of sudden changes in video content, thereby decreasing the probability of video image clarity failing to meet requirements within the acquisition interval and improving the overall video clarity.

[0061] 4. In this invention, the squirrel optimization algorithm is used to iteratively adjust the current image data acquisition interval, and the overall clarity of the played video is used as the fitness function; therefore, as the iteration proceeds, the overall clarity of the played video becomes higher and higher, eventually meeting the requirements.

[0062] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a schematic diagram of the module of the intelligent frame rate control system for OLED displays based on image analysis according to the present invention.

[0065] Figure 2 This is a flowchart illustrating the process of constructing a comprehensive state mapping model for a display screen according to the present invention.

[0066] Figure 3 This is a schematic diagram illustrating the process of constructing a display screen image sharpness mapping model according to the present invention.

[0067] Figure 4This is a flowchart illustrating the intelligent frame rate control method for OLED displays based on image analysis according to the present invention. Detailed Implementation

[0068] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0069] Example 1

[0070] Please see Figure 2-4 This embodiment describes an intelligent frame rate control method for OLED displays based on image analysis, comprising the following steps:

[0071] S1. Set several state quantity levels corresponding to several display screen state quantity types and combine them to obtain a comprehensive display screen state set.

[0072] S1 includes the following steps:

[0073] S11. Define several state variable types related to the frame rate of the OLED display, and obtain the display state variable type set a1 = {a 11 ,a 12}, a 11 a 12 These represent the dynamic level state quantity type and the complexity state quantity type of the screen, respectively. Based on the screen state quantity type set, several state quantity levels and corresponding state quantity value ranges are set for each screen state quantity type, resulting in a dynamic level level set, a dynamic level range set, a complexity level set, and a complexity range set.

[0074] The dynamic range of the image can be quantified by the speed of movement of each object on the display screen and the speed or frequency of the change of the direction of movement of the objects; the complexity of the image can be quantified by the number of objects on the display screen, the richness of texture, and the number of colors; both the dynamic range and the complexity of the image are represented by natural numbers, and the larger the value, the greater the dynamic range and the greater the complexity of the image.

[0075] S12. Combine the set of image dynamic level levels and the set of image complexity levels to obtain several comprehensive states of the OLED display screen, resulting in a set of comprehensive display screen states and a corresponding set of image dynamic complexity combinations a2; as follows.

[0076]

[0077] in, Let a and b represent the dynamic level data and the complexity level data of the i-th display screen's overall state, respectively, and let a′ represent the total number of display screen overall states obtained by combination. Each overall state in the display screen overall state set is represented by a natural number.

[0078] S2. Collect multiple historical images and corresponding comprehensive status data of the display screen when playing video based on the comprehensive status set of the display screen. Then collect the clarity data, comprehensive status data and corresponding playback frame data of the multiple historical images and construct the comprehensive status mapping model and the clarity mapping model of the display screen.

[0079] S2 includes the following steps:

[0080] S21. Set the OLED display screen that needs to be adjusted in terms of frame rate, and denot it as the display screen to be adjusted in terms of frame rate; in conjunction with the display screen overall state set, the dynamic complexity combination set, the dynamic level set, the dynamic range set, the complexity level set, and the complexity range set, collect multiple historical screen images and corresponding display screen overall state data when the display screen to be adjusted plays video, and obtain the historical display screen image dataset and the first historical display screen overall state dataset.

[0081] In addition, the clarity data, overall image status data, and frame number data of the corresponding historical images of the display screen to be adjusted are collected, as well as the frame number data of the corresponding display screen playing video, to obtain the historical image clarity dataset, the second historical display screen overall image status dataset, and the historical video playback frame number dataset.

[0082] S22. Construct a comprehensive state mapping model for the display screen using the historical display screen image dataset and the first historical display screen comprehensive state dataset.

[0083] S22 includes the following steps:

[0084] S221. Construct an initial CNN neural network model and set a first training data ratio; divide the historical display screen image dataset and the first historical display screen comprehensive state dataset according to the first training data ratio to obtain the historical display screen image training dataset, the first historical display screen comprehensive state training dataset, the historical display screen image test dataset, and the first historical display screen comprehensive state test dataset.

[0085] S222. Set a first training error threshold; use the first historical display screen image comprehensive state training dataset to label each image data in the historical display screen image training dataset to obtain a labeled historical display screen image training dataset; input the labeled historical display screen image training dataset into the initial CNN neural network model for training; during the training process, when the training error is less than the first training error threshold, stop training and obtain a trained CNN neural network model; otherwise, continue training until the training error is less than the first training error threshold.

[0086] S223. Set a first test accuracy threshold; input the historical display screen image test dataset and the first historical display screen comprehensive state test dataset as test data and test labels respectively into the trained CNN neural network model for testing; after the test is completed, obtain the first test accuracy data; when the first test accuracy data is greater than or equal to the first test accuracy threshold, use the trained CNN neural network model as the display screen comprehensive state mapping model; otherwise, return to S222 to continue training the trained CNN neural network model until the first test accuracy data is greater than or equal to the first test accuracy threshold.

[0087] CNN neural network models have the following advantages in image classification: strong feature extraction capabilities, including automatic feature learning, multi-level feature extraction, model parameter sharing, and sparse connections; they also have translation invariance, meaning they are not sensitive to image translation, making CNNs robust to changes in the position and size of objects in the image; based on the above advantages, this scheme constructs a comprehensive state mapping model for the display screen based on the CNN neural network model.

[0088] S23. Construct a display screen clarity mapping model based on the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset.

[0089] S23 includes the following steps:

[0090] S231. Construct an initial SVM model and set a second training data ratio; divide the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset according to the second training data ratio to obtain the historical image clarity training dataset, the second historical display screen image comprehensive status training dataset, the historical video playback frame count training dataset, the historical image clarity test dataset, the second historical display screen image comprehensive status test dataset, and the historical video playback frame count test dataset.

[0091] S232. Set a second training error threshold; use the second historical display screen image comprehensive status training dataset and the historical video playback frame count training dataset as training data, and use the historical image clarity training dataset as training labels to input into the initial SVM model for training; during the training process, when the training error is less than the second training error threshold, stop training and obtain the trained SVM model; otherwise, continue training until the training error is less than the second training error threshold.

[0092] S233. Set a second test accuracy threshold; use the second historical display screen image comprehensive status test dataset and the historical video playback frame count test dataset as test data, and input the historical image clarity test dataset as test labels into the trained SVM model for testing; after the test is completed, obtain the second test accuracy data; when the second test accuracy data is greater than or equal to the second test accuracy threshold, use the trained SVM model as the display screen image clarity mapping model; otherwise, return to S232 to continue training the trained SVM model until the second test accuracy data is greater than or equal to the second test accuracy threshold;

[0093] The SVM model has the following advantages in data classification: it can effectively handle high-dimensional data by mapping the data to a high-dimensional space through a kernel function, thereby finding the optimal classification hyperplane in the high-dimensional space, achieving good classification results even with high data dimensionality; its decision boundary is determined by a few support vectors, which makes the model robust and insensitive to noise and outliers in the data, maintaining good classification performance even with some noise and outliers. Based on these advantages, this solution constructs a display screen image clarity mapping model based on the SVM model.

[0094] S3. In conjunction with the display screen image comprehensive status mapping model and the display screen image clarity mapping model, the display screen image of the display screen to be adjusted is collected by setting the current image data collection interval and the corresponding current display screen image comprehensive status data is mapped out. Then the corresponding current display screen image clarity data is mapped out. Finally, the frame rate of the video played on the display screen to be adjusted is adjusted to obtain the adjusted current display screen video.

[0095] S3 includes the following steps:

[0096] S31. Set the time interval for collecting the image data of the display screen to be adjusted, and record it as the current image data collection interval; when the display screen to be adjusted is playing video, collect the image of the display screen to be adjusted according to the current image data collection interval, and use the image of the display screen to be adjusted at the current moment as the current image data of the display screen to be adjusted.

[0097] S32. Obtain the frame count data when the video is played on the display screen to be adjusted in S31, and obtain the current video playback frame count data of the display screen; input the current display screen image data to be adjusted into the display screen image comprehensive state mapping model for mapping, and obtain the current display screen image comprehensive state data of the display screen to be adjusted.

[0098] Set a first threshold for the image clarity of the display screen to be adjusted; input the current comprehensive status data of the display screen to be adjusted and the current video playback frame rate data of the display screen into the display screen image clarity mapping model for mapping to obtain the current image clarity data of the display screen to be adjusted;

[0099] S33. When the current display screen resolution data to be adjusted is less than the first display screen resolution threshold, the current display screen video playback frame rate data is adjusted to obtain the current final display screen video playback frame rate data; otherwise, it is not necessary to adjust the current display screen video playback frame rate data.

[0100] The current final display screen video playback frame rate data is used as the frame rate of the video playing on the display screen to be adjusted at the current moment;

[0101] S33 includes the following steps in adjusting the current video playback frame rate data on the display screen:

[0102] S331. Set the value range of the current display screen video playback frame rate data to obtain the current display screen video playback frame rate value range. These represent the lower limit and upper limit of the current video playback frame rate data on the display screen, respectively.

[0103] Construct a squirrel population for adjusting the video playback frame rate of the display screen; set the maximum number of iterations for the squirrel population for adjusting the video playback frame rate of the display screen to be [value missing]. And the current iteration number is These are denoted as the maximum number of iterations for frame rate adjustment and the current number of iterations for frame rate adjustment, respectively; the search space dimension for adjusting the squirrel population's video playback frame rate on the display screen is 1.

[0104] S332. Based on the current range of video playback frame rates on the display screen, adjust the initial position of each squirrel in the squirrel population by setting the video playback frame rate on the display screen to obtain a first initial position set. b 1i b'1 indicates that the initial position of the i-th squirrel in the squirrel population is adjusted by the video playback frame rate of the display screen, and b'1 indicates the size of the squirrel population is adjusted by the video playback frame rate of the display screen; b 1i The calculation formula is as follows:

[0105]

[0106] In the formula, ceil represents the floor function; rand 1i Indicates that b 1i Generate random numbers between 0 and 1;

[0107] S333. Construct the fitness function b′1 for adjusting the video playback frame rate of the display screen's squirrel population; as follows.

[0108]

[0109] In the formula, This means that the current video playback frame rate data obtained from each iteration and the corresponding current overall status data of the display screen to be adjusted are input into the display screen image clarity mapping model to obtain the image clarity data;

[0110] S334. Start the iteration. Before the iteration, set the current iteration count of the frame rate adjustment to 1. During the first iteration, use the fitness function b′1 of the display screen video playback frame rate adjustment squirrel population to calculate the fitness value of the initial position of each squirrel in the first initial position set, and obtain the first fitness value set. Take the largest fitness value in the first fitness value set and the corresponding squirrel's initial position as the first global best fitness and the first global best position, respectively. Update the initial position of each squirrel in the first initial position set according to the first global best fitness and the first global best position. After the update is completed, increment the current iteration count of the frame rate adjustment by 1 and enter the next iteration.

[0111] In each iteration, the fitness function b′1 of the display screen video playback frame rate adjustment squirrel population is used to calculate the fitness value of the position of each squirrel in the display screen video playback frame rate adjustment squirrel population updated in the previous iteration, resulting in a second fitness value set. The maximum fitness value in the second fitness value set and the corresponding squirrel position are respectively taken as the second global best fitness and the second global best position. The position of each squirrel in the display screen video playback frame rate adjustment squirrel population updated in the previous iteration is updated according to the second global best fitness and the second global best position. After the update is completed, the current iteration number of the frame rate adjustment is incremented by 1 and the next iteration is started.

[0112] S335. When a~2≥a~1, stop the iteration and obtain the first final global optimal position and the first final global optimal fitness; otherwise, continue the iteration until a~2≥a~1; use the first final global optimal fitness as the optimized current display screen image clarity data; when the optimized current display screen image clarity data is greater than or equal to the first display screen image clarity threshold, the adjustment ends and the first final global optimal position is used as the current final display screen video playback frame rate data; otherwise, return to S334 to continue the iteration until the optimized current display screen image clarity data is greater than or equal to the first display screen image clarity threshold.

[0113] By employing a squirrel optimization algorithm to iteratively adjust the number of video frames at the current moment, and using the video image clarity data at the current moment as the fitness function, the video image clarity at the current moment becomes higher and higher as the iteration progresses, eventually meeting the clarity requirements.

[0114] S34. Take the image data after the next time interval of the current display screen image data to be adjusted as the current display screen image data to be adjusted, and repeat S31, S32, S33 and S34; when the current display screen image data to be adjusted is the image data after the last time interval, stop repeating; and obtain the adjusted current display screen video.

[0115] S4. Adjust the current screen image data acquisition interval according to the adjusted current display video;

[0116] S4 includes the following steps:

[0117] S41. Set the image clarity threshold of the second display screen to be adjusted; measure the overall clarity of the adjusted current display screen video to obtain the overall clarity data of the current display screen video;

[0118] S42. When the overall clarity data of the current display screen video is less than the second display screen clarity threshold to be adjusted, the current image data acquisition interval is adjusted until the overall clarity data of the current display screen video is greater than or equal to the second display screen clarity threshold to be adjusted; otherwise, it is not necessary to adjust the current image data acquisition interval.

[0119] S42 includes the following steps in adjusting the current screen image data acquisition interval:

[0120] S421. Set the value range of the current image data acquisition interval to obtain the current acquisition interval value range. These represent the lower limit and upper limit of the current frame image data acquisition interval, respectively;

[0121] The image acquisition interval is used to adjust the squirrel population; the maximum number of iterations for adjusting the squirrel population based on the image acquisition interval is set to [value missing]. And the current iteration number is These are respectively denoted as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment; the search space dimension of the squirrel population for the image acquisition interval adjustment is 1;

[0122] S422. Based on the current acquisition interval range, adjust the initial position of each squirrel in the squirrel population by setting the image acquisition interval and obtaining the second initial position set. b 2i b'2 indicates that the image acquisition interval adjusts the initial position of the i-th squirrel in the squirrel population, and b'2 indicates that the image acquisition interval adjusts the size of the squirrel population; b 2i The calculation formula is as follows:

[0123]

[0124] In the formula, rand 2i Indicates that b 2i Generate random numbers between 0 and 1;

[0125] S423. Construct the fitness function b′2 for adjusting the image acquisition interval of the squirrel population; as follows.

[0126]

[0127] In the formula, This means replacing the current image data acquisition interval with the image acquisition interval data obtained from each iteration, and executing the adjusted overall clarity data of the current display screen video obtained from S31, S32, S33, and S34.

[0128] S424. Begin iteration. Before iteration, set the current iteration count of the interval adjustment to 1. During the first iteration, use the fitness function b′2 of the squirrel population to calculate the fitness value of the initial position of each squirrel in the second initial position set, and obtain the third fitness value set. Take the largest fitness value in the third fitness value set and the corresponding initial position of the squirrel as the third global best fitness and the third global best position, respectively. Update the initial position of each squirrel in the second initial position set according to the third global best fitness and the third global best position. After the update is completed, increment the current iteration count of the interval adjustment by 1 and enter the next iteration.

[0129] In each iteration, the fitness function b′2 of the squirrel population for adjusting the image acquisition interval is used to calculate the fitness value of the position of each squirrel in the squirrel population for adjusting the image acquisition interval obtained in the previous iteration, resulting in a fourth fitness value set. The maximum fitness value in the fourth fitness value set and the position of the corresponding squirrel are taken as the fourth global best fitness and the fourth global best position, respectively. The position of each squirrel in the squirrel population for adjusting the image acquisition interval obtained in the previous iteration is updated according to the fourth global best fitness and the fourth global best position. After the update is completed, the current iteration number of the interval adjustment is incremented by 1 and the next iteration is started.

[0130] S425. When a~4≥a~3, stop the iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue the iteration until a~4≥a~3; use the second final global optimal fitness as the optimized overall video clarity data of the current display screen; when the optimized overall video clarity data of the current display screen is greater than or equal to the second screen clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 to continue the iteration until the optimized overall video clarity data of the current display screen is greater than or equal to the second screen clarity threshold to be adjusted.

[0131] Example 2

[0132] Please see Figure 1 This embodiment discloses an intelligent frame rate control system for OLED displays based on image analysis. The system can implement the method of the above embodiment, including an OLED display state quantity level setting module, a comprehensive image state setting module, a historical display data acquisition module, a mapping model construction module, a frame rate adjustment module for the display to be adjusted, and an image acquisition interval adjustment module.

[0133] The OLED display state quantity level setting module is used to set several state quantity levels corresponding to several display state quantity types to obtain a set of dynamic level levels and a set of complex level levels.

[0134] The overall screen status setting module is used to combine the screen dynamic level set and the screen complexity level set to obtain the overall screen status set of the display screen.

[0135] The historical display screen data acquisition module is used to acquire multiple historical screen images, corresponding display screen overall status data, clarity data of multiple historical screen images, overall status data, and corresponding frame number data of the display screen playing video, based on the display screen overall status set, screen dynamic level set, and screen complexity level set, to obtain a historical display screen image dataset, a first historical display screen overall status dataset, a historical screen clarity dataset, a second historical display screen overall status dataset, and a historical video playback frame number dataset.

[0136] The mapping model construction module is used to construct a display screen image comprehensive status mapping model and a display screen image clarity mapping model based on the historical display screen image dataset, the first historical display screen image comprehensive status dataset, the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset.

[0137] The frame rate adjustment module for the display screen to be adjusted is used in conjunction with the display screen image comprehensive state mapping model and the display screen image clarity mapping model. By setting the current image data acquisition interval, it acquires the image of the display screen to be adjusted and maps the corresponding current display screen image comprehensive state data. Then, it maps the corresponding current display screen image clarity data based on the current display screen image comprehensive state data. Finally, it adjusts the frame rate of the video played on the display screen to be adjusted based on the current display screen image clarity data to obtain the adjusted current display screen video.

[0138] The image acquisition interval adjustment module is used to adjust the current image data acquisition interval based on the adjusted current display screen video.

[0139] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0140] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for intelligent frame rate control of OLED displays based on image analysis, characterized in that, Includes the following steps: S1. Set several state quantity levels corresponding to several display screen state quantity types and combine them to obtain a comprehensive display screen state set. S2. Collect multiple historical images and corresponding comprehensive status data of the display screen when playing video based on the comprehensive status set of the display screen. Then collect the clarity data, comprehensive status data and corresponding playback frame data of the multiple historical images and construct the comprehensive status mapping model and the clarity mapping model of the display screen. S3. In conjunction with the display screen image comprehensive status mapping model and the display screen image clarity mapping model, the display screen image of the display screen to be adjusted is collected by setting the current image data collection interval and the corresponding current display screen image comprehensive status data is mapped out. Then the corresponding current display screen image clarity data is mapped out. Finally, the frame rate of the video played on the display screen to be adjusted is adjusted to obtain the adjusted current display screen video. S4. Adjust the current screen image data acquisition interval according to the adjusted current display video; S4 includes the following steps: S41. Set the image clarity threshold of the second display screen to be adjusted; measure the overall clarity of the adjusted current display screen video to obtain the overall clarity data of the current display screen video; S42. When the overall clarity data of the current display screen video is less than the second display screen clarity threshold to be adjusted, the current image data acquisition interval is adjusted until the overall clarity data of the current display screen video is greater than or equal to the second display screen clarity threshold to be adjusted; otherwise, there is no need to adjust the current image data acquisition interval.

2. The intelligent frame rate control method for OLED displays based on image analysis according to claim 1, characterized in that, S1 includes the following steps: S11. Set several state quantity types related to the frame rate of the OLED display to obtain a display state quantity type set; set several state quantity levels and corresponding state quantity value ranges for each display state quantity type according to the display state quantity type set to obtain a set of screen dynamic level levels, a set of screen dynamic level ranges, a set of screen complexity levels, and a set of screen complexity ranges. S12. Combine the set of dynamic level of the screen and the set of screen complexity to obtain several comprehensive states of the OLED display screen, and obtain the set of comprehensive screen states and the corresponding set of dynamic level of screen complexity combinations.

3. The intelligent frame rate control method for OLED displays based on image analysis according to claim 2, characterized in that, S2 includes the following steps: S21. Set the OLED display screen that needs to be adjusted in terms of frame rate, and denot it as the display screen to be adjusted in terms of frame rate; in conjunction with the display screen overall state set, the dynamic complexity combination set, the dynamic level set, the dynamic range set, the complexity level set, and the complexity range set, collect multiple historical screen images and corresponding display screen overall state data when the display screen to be adjusted plays video, and obtain the historical display screen image dataset and the first historical display screen overall state dataset. In addition, the clarity data, overall image status data, and frame number data of the corresponding historical images of the display screen to be adjusted are collected, as well as the frame number data of the corresponding display screen playing video, to obtain the historical image clarity dataset, the second historical display screen overall image status dataset, and the historical video playback frame number dataset. S22. Construct a comprehensive state mapping model for the display screen using the historical display screen image dataset and the first historical display screen comprehensive state dataset. S23. Construct a display screen image clarity mapping model based on the historical image clarity dataset, the second historical display screen image comprehensive status dataset, and the historical video playback frame count dataset.

4. The intelligent frame rate control method for OLED displays based on image analysis according to claim 3, characterized in that: The display screen image comprehensive state mapping model described in S22 adopts a CNN neural network model.

5. The intelligent frame rate control method for OLED displays based on image analysis according to claim 4, characterized in that: The display screen image clarity mapping model described in S23 adopts the SVM model.

6. The intelligent frame rate control method for OLED displays based on image analysis according to claim 5, characterized in that, S3 includes the following steps: S31. Set the time interval for collecting the image data of the display screen to be adjusted, and record it as the current image data collection interval; when the display screen to be adjusted is playing video, collect the image of the display screen to be adjusted according to the current image data collection interval, and use the image of the display screen to be adjusted at the current moment as the current image data of the display screen to be adjusted. S32. Obtain the frame count data when the video is played on the display screen to be adjusted in S31, and obtain the current video playback frame count data of the display screen; input the current display screen image data to be adjusted into the display screen image comprehensive state mapping model for mapping, and obtain the current display screen image comprehensive state data of the display screen to be adjusted. Set a first threshold for the image clarity of the display screen to be adjusted; input the current comprehensive status data of the display screen to be adjusted and the current video playback frame rate data of the display screen into the display screen image clarity mapping model for mapping to obtain the current image clarity data of the display screen to be adjusted; S33. When the current display screen resolution data to be adjusted is less than the first display screen resolution threshold, the current display screen video playback frame rate data is adjusted to obtain the current final display screen video playback frame rate data; otherwise, it is not necessary to adjust the current display screen video playback frame rate data. The current final display screen video playback frame rate data is used as the frame rate of the video playing on the display screen to be adjusted at the current moment; S34. Take the image data after the next time interval of the current display screen image data as the current display screen image data, and repeat S31, S32, S33 and S34; when the current display screen image data is the image data after the last time interval, stop repeating; and obtain the adjusted current display screen video.

7. The intelligent frame rate control method for OLED displays based on image analysis according to claim 6, characterized in that: In S33, the adjustment of the current video playback frame rate data on the display screen is performed using a squirrel optimization algorithm.

8. The intelligent frame rate control method for OLED displays based on image analysis according to claim 7, characterized in that, S42 includes the following steps in adjusting the current screen image data acquisition interval: S421. Set the value range of the current image data acquisition interval to obtain the current acquisition interval value range; construct an image acquisition interval adjustment squirrel population; set the maximum number of iterations for the image acquisition interval adjustment squirrel population to be... And the current iteration number is These are respectively denoted as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment; S422. Based on the current acquisition interval range, set the image acquisition interval and adjust the initial position of each squirrel in the squirrel population to obtain a second initial position set. S423. Construct the fitness function for adjusting the squirrel population based on the image acquisition interval; S424. Start the iteration. Before the iteration, set the current iteration number of the interval adjustment to 1. During each iteration, use the fitness function of the image acquisition interval adjustment squirrel population to calculate the fitness value of the position of each squirrel in the image acquisition interval adjustment squirrel population updated in the previous iteration and update the position of each squirrel in the image acquisition interval adjustment squirrel population updated in the previous iteration. S425, when If the condition is met, stop the iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue the iteration until... Up to this point; the second final global best fitness is used as the optimized overall clarity data of the current display screen video; when the optimized overall clarity data of the current display screen video is greater than or equal to the second display screen image clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 to continue iterating until the optimized overall clarity data of the current display screen video is greater than or equal to the second display screen image clarity threshold to be adjusted.

9. A system for implementing the image analysis-based intelligent frame rate control method for OLED displays as described in any one of claims 1-8.

Images